© 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 EvalsExportsAPI 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. 1174
    Prev
    Next
    INDEX
    Explanations

    text related to programming and technical instructions

    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
    288
    +0.15
    0.6%
    326
    +0.14
    0.6%
    249
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.19
    326
    +0.14
    0.15
    575
    +0.13
    0.14
    Negative Logits
    romy
    -0.92
    itions
    -0.89
     Pradesh
    -0.88
    edu
    -0.87
    ition
    -0.81
    maxwell
    -0.81
    ori
    -0.80
    equality
    -0.78
    ¥ŀ
    -0.78
    lyak
    -0.76
    POSITIVE LOGITS
     extraord
    1.34
     beware
    1.04
    sonian
    0.96
    stown
    0.85
    llan
    0.85
    BIL
    0.84
    oute
    0.82
    getic
    0.79
    maid
    0.78
    GUI
    0.77
    Activations Density 4.161%

    No Known Activations