© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    keywords related to utilizing or needing assistance or resources

    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
    628
    +0.08
    0.5%
    68
    +0.07
    0.5%
    614
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.08
    0.02
    7
    +0.07
    0.02
    28
    +0.06
    0.02
    Negative Logits
    ALSE
    -0.49
     manifest
    -0.48
     bankrupt
    -0.47
     unequ
    -0.47
     undertaken
    -0.44
     derog
    -0.43
     undertaking
    -0.43
    akable
    -0.43
     unsupported
    -0.43
    sis
    -0.42
    POSITIVE LOGITS
     Kris
    0.48
     Aging
    0.48
     Bows
    0.46
    noon
    0.43
     Lots
    0.42
     Ging
    0.42
    orage
    0.42
     Beet
    0.42
    ILY
    0.42
     Crack
    0.41
    Activations Density 0.038%

    No Known Activations