© 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
    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. 4023
    Prev
    Next
    INDEX
    Explanations

    references to cooking-related terms, activities, and ingredients

    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
    +0.23
    0.9%
    220
    +0.13
    0.5%
    16
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.23
    0.18
    48
    +0.13
    0.08
    749
    +0.12
    0.07
    Negative Logits
    umbn
    -0.87
    ertodd
    -0.85
    orporated
    -0.79
    emale
    -0.79
    venants
    -0.78
    orb
    -0.77
     Baghd
    -0.75
    idas
    -0.72
    vernment
    -0.70
     Citizens
    -0.69
    POSITIVE LOGITS
    books
    1.05
    stall
    0.99
     cooks
    0.98
    book
    0.95
    cook
    0.91
     cook
    0.91
     stove
    0.89
    ieri
    0.88
    Cook
    0.86
    washer
    0.86
    Activations Density 5.977%

    No Known Activations