Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 44952
    Prev
    Next
    INDEX
    Explanations

    text related to labor, employment, and workforce conditions

    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
    288
    +0.16
    0.7%
    447
    +0.16
    0.7%
    575
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.16
    0.07
    636
    +0.16
    0.07
    518
    +0.13
    0.10
    Negative Logits
    irs
    -0.89
     Flavoring
    -0.88
     Seym
    -0.72
     Qiao
    -0.70
    resy
    -0.69
     Nib
    -0.69
     Mons
    -0.68
     Ack
    -0.67
     Gamble
    -0.67
    opal
    -0.66
    POSITIVE LOGITS
     labor
    0.95
     unions
    0.93
    union
    0.87
     intensive
    0.86
     stopp
    0.84
    Union
    0.82
     union
    0.79
    iously
    0.78
    abor
    0.78
    urg
    0.78
    Activations Density 9.429%

    No Known Activations