© 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. 11565
    Prev
    Next
    INDEX
    Explanations

    numerical values or estimates in texts

    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
    57
    +0.16
    0.5%
    151
    +0.16
    0.5%
    289
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.16
    0.06
    101
    +0.16
    0.06
    725
    +0.15
    0.04
    Negative Logits
    oa
    -1.15
    ysis
    -1.10
    oli
    -1.01
    alez
    -0.99
     Bomber
    -0.99
    rosis
    -0.99
    ters
    -0.98
    TB
    -0.97
    aretz
    -0.93
    ole
    -0.92
    POSITIVE LOGITS
     analogous
    1.16
    Ĥİ
    1.12
     approximate
    1.09
     equivalent
    1.08
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    1.07
    Ń·
    1.01
    ãĤ©
    0.99
    PsyNetMessage
    0.97
     sized
    0.96
     populated
    0.96
    Activations Density 0.581%

    No Known Activations