© 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. 10121
    Prev
    Next
    INDEX
    Explanations

    financial and fundraising related terms

    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
    +0.16
    0.7%
    635
    +0.13
    0.6%
    352
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.10
    174
    +0.13
    0.05
    352
    +0.12
    0.06
    Negative Logits
    atar
    -0.86
    ĨĴ
    -0.79
    ox
    -0.74
    amura
    -0.74
    ient
    -0.74
    RAL
    -0.73
    pur
    -0.72
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.72
    pher
    -0.71
    phis
    -0.71
    POSITIVE LOGITS
     laundering
    0.84
    woman
    0.84
     scams
    0.80
     commissions
    0.80
     donors
    0.79
     PACs
    0.79
     backer
    0.77
     dinners
    0.77
     solicitation
    0.77
    aires
    0.76
    Activations Density 1.111%

    No Known Activations