Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45314
    Prev
    Next
    INDEX
    Explanations

    mentions of the prefix "Aut" or "Auto" followed by numbers or specific words

    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
    754
    +0.09
    0.6%
    60
    +0.09
    0.6%
    575
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.09
    0.09
    637
    +0.09
    0.10
    232
    +0.09
    0.09
    Negative Logits
    imaru
    -0.54
    ITED
    -0.52
     Birch
    -0.51
     tobacco
    -0.48
     tuna
    -0.47
    ardless
    -0.47
     smokes
    -0.46
     Krishna
    -0.46
     Chandra
    -0.46
    çķ
    -0.46
    POSITIVE LOGITS
    onomous
    0.86
    opsy
    0.82
    omatic
    0.72
    odes
    0.72
    onomy
    0.66
    ilus
    0.62
    imov
    0.62
    immune
    0.61
    istic
    0.61
    auga
    0.60
    Activations Density 5.208%

    No Known Activations