© 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. 33004
    Prev
    Next
    INDEX
    Explanations

    references to technical and political processes

    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
    +0.19
    1.2%
    679
    +0.09
    0.5%
    683
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.19
    0.25
    225
    +0.09
    0.13
    370
    +0.08
    0.09
    Negative Logits
     Adventures
    -0.47
     Recon
    -0.45
     Travels
    -0.45
     Somers
    -0.44
     Rocket
    -0.44
     LIFE
    -0.43
     Sanctuary
    -0.43
     Shooter
    -0.42
     Cadillac
    -0.41
     Stability
    -0.41
    POSITIVE LOGITS
    mith
    0.83
    ourcing
    0.74
    pring
    0.74
    poons
    0.70
    ourced
    0.68
    ynthesis
    0.67
    umatic
    0.67
    paces
    0.66
    heet
    0.65
    creen
    0.65
    Activations Density 12.580%

    No Known Activations