© 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. 4140
    Prev
    Next
    INDEX
    Explanations

    information related to laws and legislation in various states

    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
    258
    +0.11
    0.6%
    447
    +0.08
    0.5%
    581
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.11
    0.09
    258
    +0.08
    0.16
    620
    +0.07
    0.03
    Negative Logits
    bor
    -0.67
     Grave
    -0.64
    hod
    -0.63
    raid
    -0.60
    gotten
    -0.59
    rious
    -0.55
    othy
    -0.54
    chel
    -0.53
    Py
    -0.52
    chie
    -0.52
    POSITIVE LOGITS
     nationwide
    0.69
     legislatures
    0.63
     statewide
    0.61
    wide
    0.61
     counties
    0.61
     vying
    0.59
     including
    0.58
     supermarkets
    0.57
     across
    0.56
     nationally
    0.56
    Activations Density 12.636%

    No Known Activations