© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10139
    Prev
    Next
    INDEX
    Explanations

    information related to labor, employment, wages, and working conditions in various contexts and regions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.25
    0.9%
    575
    +0.16
    0.6%
    624
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.25
    0.09
    288
    +0.16
    0.08
    116
    +0.14
    0.05
    Negative Logits
    irs
    -1.06
     Flavoring
    -0.98
    resy
    -0.90
     Seym
    -0.90
    gran
    -0.82
     Mons
    -0.81
     Buckingham
    -0.79
    eger
    -0.78
    apa
    -0.78
    opal
    -0.78
    POSITIVE LOGITS
     unions
    1.09
     labor
    1.04
    union
    1.02
    geist
    1.00
    urg
    0.97
     gloves
    0.96
    iously
    0.94
    atories
    0.93
    ayers
    0.93
    force
    0.93
    Activations Density 1.269%

    No Known Activations