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

    Neuronpedia

    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. 14404
    Prev
    Next
    INDEX
    Explanations

    numbers in specific formats

    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
    740
    +0.04
    0.5%
    265
    +0.04
    0.4%
    65
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.04
    0.01
    333
    +0.04
    0.01
    581
    +0.04
    0.01
    Negative Logits
    lication
    -0.33
     respectively
    -0.30
    SPONSORED
    -0.30
     profit
    -0.29
    Sov
    -0.29
    Hit
    -0.29
    $.
    -0.29
     Sacrifice
    -0.28
    ¢
    -0.28
    (*
    -0.28
    POSITIVE LOGITS
    iffe
    0.35
    bart
    0.33
    iffin
    0.32
     Bailey
    0.32
    abee
    0.32
    oppy
    0.31
     Leah
    0.31
    oyd
    0.31
    Poll
    0.31
     Bunny
    0.30
    Activations Density 0.022%

    No Known Activations