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. 45369
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and software

    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
    +0.31
    1.6%
    393
    +0.22
    1.1%
    554
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.31
    0.20
    43
    +0.22
    0.18
    393
    +0.10
    0.29
    Negative Logits
    raved
    -0.63
    ¬¼
    -0.59
    abouts
    -0.57
    nell
    -0.55
    riad
    -0.55
     mosquit
    -0.53
    rup
    -0.53
    rament
    -0.53
    rophe
    -0.52
    usra
    -0.52
    POSITIVE LOGITS
     namely
    1.07
     including
    1.01
     thereby
    1.01
     respectively
    1.00
     preferably
    0.97
     regardless
    0.96
     whereas
    0.95
     irrespective
    0.95
     etc
    0.95
     INCLUD
    0.93
    Activations Density 12.635%

    No Known Activations