© 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. 6135
    Prev
    Next
    INDEX
    Explanations

    mentions of online interactions, sign-ups, and digital subscriptions

    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
    +0.07
    0.5%
    245
    +0.07
    0.4%
    487
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.07
    0.02
    62
    +0.07
    0.02
    13
    +0.07
    0.03
    Negative Logits
    itudinal
    -0.56
     Pwr
    -0.52
    ificial
    -0.52
    PLIED
    -0.51
     buffet
    -0.48
    heit
    -0.47
    rontal
    -0.47
     Triangle
    -0.46
    qqa
    -0.45
     triangle
    -0.44
    POSITIVE LOGITS
    aged
    0.63
    rules
    0.50
    eda
    0.50
    shows
    0.49
    rade
    0.48
    oys
    0.47
     elig
    0.46
    ocl
    0.46
    rals
    0.46
    aware
    0.46
    Activations Density 0.113%

    No Known Activations