© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2385
    Prev
    Next
    INDEX
    Explanations

    scientific and academic terms and phrases, specifically related to research, student assessments, and technical applications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    391
    +0.05
    0.4%
    610
    +0.05
    0.4%
    576
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.05
    0.01
    373
    +0.05
    -0.01
    167
    +0.05
    0.00
    Negative Logits
     signific
    -0.38
    soType
    -0.37
     Architects
    -0.37
    holders
    -0.35
     Runes
    -0.35
    isms
    -0.34
    RGB
    -0.34
    rawdownloadcloneembedreportprint
    -0.33
    stakes
    -0.33
     Advertisement
    -0.33
    POSITIVE LOGITS
    iage
    0.43
    jj
    0.38
    riage
    0.36
    achus
    0.35
     drafts
    0.35
     boxer
    0.34
     shorts
    0.34
    atche
    0.34
    Synopsis
    0.33
     Citiz
    0.33
    Activations Density 0.050%

    No Known Activations