© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    information related to mythical creatures and fantasy worlds

    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
    35
    +0.17
    0.6%
    522
    +0.15
    0.5%
    23
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.15
    288
    +0.15
    0.18
    48
    +0.15
    0.09
    Negative Logits
    20439
    -0.96
    NetMessage
    -0.95
     Jackets
    -0.93
     Communication
    -0.92
    eper
    -0.92
     Process
    -0.92
     Oval
    -0.92
     Proced
    -0.91
     Parenthood
    -0.90
     Cause
    -0.90
    POSITIVE LOGITS
    arious
    1.36
    ovan
    1.24
    bled
    1.23
    asses
    1.19
    wart
    1.16
    king
    1.15
    bling
    1.15
    esses
    1.14
    aji
    1.14
    stein
    1.13
    Activations Density 2.989%

    No Known Activations