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. 13613
    Prev
    Next
    INDEX
    Explanations

    numbers related to measurements such as weight, capacity, and cost

    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
    +0.28
    1.3%
    432
    +0.14
    0.6%
    570
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.28
    0.14
    570
    +0.14
    0.05
    193
    +0.11
    0.12
    Negative Logits
    Synopsis
    -0.68
    ctor
    -0.61
     groom
    -0.59
    opol
    -0.58
    ormal
    -0.58
    scripts
    -0.57
    ãĥķãĤ©
    -0.56
     orchestr
    -0.56
    ãĥĦ
    -0.55
    lict
    -0.54
    POSITIVE LOGITS
     apiece
    0.93
     increments
    0.91
    +.
    0.72
    alion
    0.71
    /$
    0.69
    amiya
    0.68
    tein
    0.67
     thereafter
    0.65
     total
    0.64
     onwards
    0.64
    Activations Density 7.288%

    No Known Activations