© 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. 13654
    Prev
    Next
    INDEX
    Explanations

    instances of the word "disclosure"

    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
    1.1%
    441
    +0.14
    0.7%
    288
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.23
    0.03
    362
    +0.14
    0.12
    195
    +0.14
    -0.02
    Negative Logits
    ieval
    -0.69
    anova
    -0.68
    vic
    -0.66
    isol
    -0.66
    swick
    -0.65
    creation
    -0.64
    Äį
    -0.63
    clock
    -0.63
    inal
    -0.62
    IAN
    -0.62
    POSITIVE LOGITS
     disclosure
    0.91
     disclosures
    0.88
     disclosing
    0.84
     loopholes
    0.82
     disclose
    0.82
     discl
    0.77
     Disclosure
    0.75
     wrongdoing
    0.71
     acknowled
    0.70
     srfAttach
    0.69
    Activations Density 11.291%

    No Known Activations