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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 34545
    Prev
    Next
    INDEX
    Explanations

    words related to labor force, job market, and employment

    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
    668
    +0.08
    0.4%
    383
    +0.07
    0.4%
    761
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.18
    575
    +0.07
    0.13
    225
    +0.07
    0.09
    Negative Logits
    ãĤ±
    -0.85
    é¾
    -0.80
    ivas
    -0.69
    argon
    -0.64
    sbm
    -0.63
    ocol
    -0.62
    DragonMagazine
    -0.62
    edi
    -0.60
    isl
    -0.59
     Nanto
    -0.59
    POSITIVE LOGITS
     statistic
    0.67
     uninsured
    0.66
    mma
    0.66
     workforce
    0.58
     wage
    0.56
     Gap
    0.55
     turnout
    0.55
     healthier
    0.54
     depression
    0.54
     Marino
    0.54
    Activations Density 4.656%

    No Known Activations