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. 13463
    Prev
    Next
    INDEX
    Explanations

    text related to quantities and comparisons of values

    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
    +0.18
    0.8%
    646
    +0.10
    0.4%
    108
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.18
    0.09
    35
    +0.10
    0.09
    384
    +0.09
    0.06
    Negative Logits
    Reviewer
    -0.74
     ``
    -0.66
    \":
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    ****************
    -0.64
     \"
    -0.63
    ################
    -0.63
    Word
    -0.62
    Tweet
    -0.61
    ="#
    -0.60
    POSITIVE LOGITS
    depending
    1.24
     depending
    1.01
     respectively
    1.00
    undai
    0.79
    levels
    0.78
     inclusive
    0.74
    auri
    0.70
    ritch
    0.70
    fff
    0.69
    cycles
    0.69
    Activations Density 20.616%

    No Known Activations