© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    copyright symbols or mentions of intellectual property rights

    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
    151
    +0.17
    0.6%
    164
    +0.16
    0.5%
    746
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.17
    0.03
    524
    +0.16
    0.02
    559
    +0.14
    0.02
    Negative Logits
    rency
    -0.96
    atem
    -0.95
    cknow
    -0.93
     detached
    -0.88
    ouch
    -0.87
    nesia
    -0.87
     plain
    -0.86
    tl
    -0.86
     Admir
    -0.85
     assum
    -0.84
    POSITIVE LOGITS
     Copyright
    1.30
    Copyright
    1.29
    ©
    1.16
    POL
    1.08
    CLOSE
    1.02
    DOC
    1.01
    EPA
    0.91
    PET
    0.91
     Provided
    0.90
    ombat
    0.90
    Activations Density 0.079%

    No Known Activations