Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34102
    Prev
    Next
    INDEX
    Explanations

    personal experiences, emotions, and reflections related to identity and relationships

    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
    1.2%
    393
    +0.12
    0.6%
    366
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.27
    0.12
    566
    +0.12
    0.12
    169
    +0.12
    0.13
    Negative Logits
    idth
    -0.62
     STA
    -0.61
     Provided
    -0.61
    rising
    -0.58
     Ways
    -0.57
     Circuit
    -0.57
    earchers
    -0.57
     Larson
    -0.56
     Races
    -0.56
     Coalition
    -0.55
    POSITIVE LOGITS
     feel
    0.88
     realize
    0.85
     ineligible
    0.83
     hesitate
    0.82
     reconsider
    0.79
     realise
    0.77
     uneasy
    0.76
     eligible
    0.76
     believe
    0.75
     look
    0.75
    Activations Density 10.963%

    No Known Activations