© 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. 45804
    Prev
    Next
    INDEX
    Explanations

    mentions of jobs, skills, workers, and labor in the context of workforce development and industry

    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
    +0.29
    1.3%
    71
    +0.13
    0.6%
    575
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.29
    0.23
    537
    +0.13
    0.15
    351
    +0.12
    0.06
    Negative Logits
    ļéĨĴ
    -0.86
     Gawker
    -0.67
     Dreams
    -0.67
    ģĸ
    -0.66
    ¹
    -0.65
    cknow
    -0.65
    raham
    -0.65
    £
    -0.64
     Rape
    -0.63
     Products
    -0.63
    POSITIVE LOGITS
    hip
    1.33
    hips
    1.19
    ourced
    0.89
     capable
    0.86
     willing
    0.84
    pace
    0.84
     roaming
    0.83
     stationed
    0.82
     recruited
    0.79
    paces
    0.74
    Activations Density 16.873%

    No Known Activations