Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40266
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.16
    0.7%
    288
    +0.15
    0.7%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.20
    326
    +0.15
    0.18
    538
    +0.11
    0.06
    Negative Logits
    versions
    -0.76
    IENCE
    -0.74
    cers
    -0.67
    nces
    -0.65
    nce
    -0.64
    yrinth
    -0.63
    realDonaldTrump
    -0.63
    ¹
    -0.63
    payer
    -0.62
    ricular
    -0.62
    POSITIVE LOGITS
    creen
    0.96
    berg
    0.93
    olini
    0.89
    es
    0.89
     Rocks
    0.78
    ett
    0.77
    abee
    0.76
     Moss
    0.75
    abis
    0.74
    ack
    0.74
    Activations Density 4.851%

    No Known Activations