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. 34598
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and software development

    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
    +0.34
    1.6%
    420
    +0.13
    0.6%
    665
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.34
    0.09
    318
    +0.13
    0.07
    554
    +0.12
    -0.05
    Negative Logits
     Hai
    -0.72
    nesty
    -0.69
    bitious
    -0.67
     Tale
    -0.67
    gdala
    -0.66
     Rid
    -0.62
     Ariel
    -0.60
    odore
    -0.60
     Chomsky
    -0.59
    ipeg
    -0.58
    POSITIVE LOGITS
     sparing
    0.95
    fully
    0.84
     interchange
    0.83
     extensively
    0.78
     exclusively
    0.72
    pez
    0.70
    nesday
    0.69
    MSN
    0.69
    FUL
    0.67
    ences
    0.66
    Activations Density 5.629%

    No Known Activations