© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34765
    Prev
    Next
    INDEX
    Explanations

    content related to formal statements or public relations apologies

    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
    393
    +0.24
    1.3%
    447
    +0.21
    1.2%
    608
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.24
    0.29
    393
    +0.21
    0.29
    385
    +0.13
    0.28
    Negative Logits
     Canaver
    -0.65
     anew
    -0.64
    ourney
    -0.62
    elman
    -0.61
    NB
    -0.60
    %%%%
    -0.59
    azel
    -0.59
    pport
    -0.58
    SPONSORED
    -0.56
    dar
    -0.56
    POSITIVE LOGITS
     sexes
    1.21
     extremes
    0.78
     aforementioned
    0.77
     latter
    0.77
     ages
    0.76
     genders
    0.72
     respective
    0.72
     parties
    0.68
     smallest
    0.67
     two
    0.66
    Activations Density 7.090%

    No Known Activations