© 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. 39974
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions of societal issues, legal concepts, and comparisons of situations

    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
    +0.27
    1.7%
    393
    +0.11
    0.6%
    724
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.28
    703
    +0.11
    0.10
    172
    +0.07
    0.11
    Negative Logits
    bard
    -0.50
    bern
    -0.50
    akia
    -0.49
    yan
    -0.49
    zzi
    -0.48
    ega
    -0.48
    hole
    -0.46
    ird
    -0.45
    shaw
    -0.45
    fine
    -0.44
    POSITIVE LOGITS
    soever
    0.81
    fy
    0.62
     comparing
    0.55
     confronted
    0.55
     compared
    0.55
    irlf
    0.53
     contrasted
    0.52
     faced
    0.52
     applied
    0.49
    iquid
    0.48
    Activations Density 12.815%

    No Known Activations