© 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. 7102
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to existing things or concepts

    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
    339
    +0.17
    0.6%
    288
    +0.13
    0.5%
    423
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.17
    0.08
    339
    +0.13
    0.06
    91
    +0.12
    0.06
    Negative Logits
    ousse
    -1.13
    xtap
    -0.99
    ertodd
    -0.97
    pper
    -0.95
    ervatives
    -0.94
    aminer
    -0.93
    ogun
    -0.93
    ices
    -0.93
    jah
    -0.93
    cher
    -0.92
    POSITIVE LOGITS
    foundland
    1.11
     arrangements
    1.10
     repertoire
    1.04
     liabilities
    1.02
    entials
    1.02
     engagements
    0.98
     quo
    0.94
     tenant
    0.93
     testament
    0.93
    NESS
    0.92
    Activations Density 1.327%

    No Known Activations