© 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. 45831
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues

    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%
    481
    +0.15
    0.6%
    679
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.30
    718
    +0.15
    0.17
    452
    +0.14
    0.09
    Negative Logits
    effic
    -0.84
     diseases
    -0.73
    advant
    -0.72
    efficiency
    -0.71
     laure
    -0.69
     habitat
    -0.69
     Columb
    -0.69
     competition
    -0.68
     shortages
    -0.68
    ahime
    -0.68
    POSITIVE LOGITS
     excerpts
    1.17
     reprinted
    1.14
    itled
    1.12
     published
    1.07
     excerpt
    1.03
     redacted
    1.03
     leaked
    1.00
     headlined
    0.98
     circulated
    0.98
     edited
    0.96
    Activations Density 15.079%

    No Known Activations