© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    locations related to space missions or geographical features like parks and towns

    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
    238
    +0.12
    0.7%
    326
    +0.10
    0.6%
    420
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.04
    551
    +0.10
    0.06
    476
    +0.09
    0.02
    Negative Logits
    amine
    -0.63
    arial
    -0.62
    naires
    -0.59
    agi
    -0.59
    omen
    -0.58
    atically
    -0.57
    perse
    -0.57
    swer
    -0.57
    orno
    -0.54
    arily
    -0.53
    POSITIVE LOGITS
    llan
    0.94
     Cod
    0.87
     Canaveral
    0.83
    lla
    0.82
     Coast
    0.72
     Coral
    0.70
     Rim
    0.67
     Colony
    0.66
     Town
    0.65
     Cape
    0.65
    Activations Density 5.203%

    No Known Activations