© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13730
    Prev
    Next
    INDEX
    Explanations

    references to wages, including wage growth, wage inequality, and related economic concepts such as productivity and surplus value

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.18
    0.6%
    575
    +0.17
    0.5%
    620
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.18
    0.04
    288
    +0.17
    0.06
    575
    +0.15
    0.05
    Negative Logits
    20439
    -1.24
    obyl
    -1.23
    NetMessage
    -1.10
    DEP
    -0.98
     Moff
    -0.98
    umbn
    -0.95
     Blossom
    -0.95
    yss
    -0.94
     Crom
    -0.93
     Chimera
    -0.93
    POSITIVE LOGITS
     earners
    1.73
    wage
    1.36
     labor
    1.18
     labour
    1.18
     labou
    1.17
    cloth
    1.13
    checks
    1.13
     wage
    1.13
     rent
    1.12
    payers
    1.11
    Activations Density 0.599%

    No Known Activations