© 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. 12801
    Prev
    Next
    INDEX
    Explanations

    reporting or news-related phrases

    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
    186
    +0.04
    0.5%
    479
    +0.04
    0.4%
    616
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.04
    0.01
    591
    +0.04
    0.01
    508
    +0.04
    0.01
    Negative Logits
    upon
    -0.30
    vice
    -0.28
    tur
    -0.28
    arch
    -0.28
    shall
    -0.27
    dash
    -0.27
    Pg
    -0.27
    itably
    -0.27
    onto
    -0.26
    annot
    -0.26
    POSITIVE LOGITS
    senal
    0.33
     AUTH
    0.29
     Emblem
    0.28
     Actual
    0.27
     Tanaka
    0.27
     Selling
    0.27
     Scale
    0.27
     FTA
    0.26
     START
    0.26
     Exhibit
    0.26
    Activations Density 0.040%

    No Known Activations