© 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. 33147
    Prev
    Next
    INDEX
    Explanations

    words related to actions and events with potential consequences

    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
    75
    +0.07
    0.5%
    504
    +0.07
    0.5%
    212
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.07
    0.08
    125
    +0.07
    0.10
    240
    +0.07
    0.10
    Negative Logits
    ortment
    -0.57
    Filename
    -0.50
    OGR
    -0.45
    unker
    -0.43
    pse
    -0.42
    lik
    -0.42
    Form
    -0.41
    xual
    -0.40
    cible
    -0.40
    tein
    -0.40
    POSITIVE LOGITS
     Brist
    0.47
     Fargo
    0.43
    MIT
    0.43
     Rothschild
    0.42
     omin
    0.41
     Rossi
    0.41
     Clapper
    0.41
     Dame
    0.41
    },"
    0.41
    OPA
    0.40
    Activations Density 14.107%

    No Known Activations