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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 40157
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming languages and coding syntax, specifically involving PHP and programming structures

    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
    383
    +0.13
    0.5%
    709
    +0.12
    0.5%
    444
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.13
    0.06
    299
    +0.12
    0.09
    6
    +0.12
    0.10
    Negative Logits
    kefeller
    -0.89
    ernels
    -0.85
    paralle
    -0.85
    keyes
    -0.83
    hips
    -0.77
    iosity
    -0.77
    rama
    -0.74
    inyl
    -0.73
    olor
    -0.71
    rieved
    -0.71
    POSITIVE LOGITS
    asure
    1.47
    anwhile
    1.44
    lda
    1.30
    zzo
    1.23
    ister
    1.14
    asured
    1.11
    forth
    1.10
    isters
    1.10
    adows
    1.07
    leon
    1.07
    Activations Density 5.254%

    No Known Activations