© 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. 8233
    Prev
    Next
    INDEX
    Explanations

    questions or prompts directed at the reader

    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
    354
    +0.14
    0.5%
    326
    +0.13
    0.5%
    762
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.08
    566
    +0.13
    0.07
    762
    +0.13
    0.08
    Negative Logits
    assembly
    -1.10
    ooks
    -0.95
    atlantic
    -0.94
    76561
    -0.93
    behind
    -0.91
    pict
    -0.91
    links
    -0.89
    assemb
    -0.88
     Making
    -0.88
    photos
    -0.87
    POSITIVE LOGITS
     succeed
    1.25
     be
    1.22
     ever
    1.20
     abandon
    1.19
     recognise
    1.17
     accept
    1.17
     dare
    1.15
     resolve
    1.11
     tolerate
    1.10
     receive
    1.08
    Activations Density 0.870%

    No Known Activations