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. 34385
    Prev
    Next
    INDEX
    Explanations

    phrases related to written content such as news stories, newsletters, advertisements, and fictional narratives

    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
    +0.14
    0.8%
    486
    +0.09
    0.5%
    564
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.37
    6
    +0.09
    0.22
    160
    +0.09
    0.25
    Negative Logits
    boro
    -0.65
     bos
    -0.55
    ethy
    -0.53
    Zone
    -0.51
    owship
    -0.51
    zynski
    -0.50
    haps
    -0.50
    igslist
    -0.49
    onde
    -0.48
    thur
    -0.48
    POSITIVE LOGITS
    %]
    0.59
    morning
    0.57
    window
    0.55
    duction
    0.51
     wrestle
    0.51
    gallery
    0.50
     gripping
    0.49
    ellen
    0.48
     cartoons
    0.47
    Prev
    0.46
    Activations Density 15.542%

    No Known Activations