© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research methods and numerical data

    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
    508
    +0.14
    0.5%
    169
    +0.12
    0.5%
    616
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.14
    0.01
    545
    +0.12
    0.01
    699
    +0.11
    0.01
    Negative Logits
    atche
    -0.87
    ommel
    -0.79
    olver
    -0.76
     Guilty
    -0.75
    osition
    -0.75
    âĻ¥
    -0.74
    YL
    -0.74
     Grimoire
    -0.73
     Palest
    -0.73
    ibel
    -0.73
    POSITIVE LOGITS
    ¥µ
    1.13
     sd
    0.91
     ±
    0.90
    ±
    0.87
    ¿
    0.82
    ĻĤ
    0.78
    ĺħ
    0.77
    İĭ
    0.76
    eatures
    0.76
    Ľ
    0.76
    Activations Density 0.052%

    No Known Activations