© 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. 3048
    Prev
    Next
    INDEX
    Explanations

    financial and budget related information

    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
    393
    +0.25
    1.0%
    608
    +0.15
    0.6%
    647
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.25
    0.09
    647
    +0.15
    0.06
    589
    +0.15
    0.06
    Negative Logits
    bender
    -0.84
    bro
    -0.79
    herer
    -0.79
    arted
    -0.76
    edd
    -0.75
    lance
    -0.74
     Entered
    -0.74
    ogan
    -0.74
    abul
    -0.73
    azz
    -0.73
    POSITIVE LOGITS
     ours
    0.88
     bedrock
    0.82
     insure
    0.81
     compensate
    0.79
     inverse
    0.78
     subsistence
    0.78
     minimize
    0.76
     avoid
    0.76
     zero
    0.75
     honor
    0.75
    Activations Density 0.991%

    No Known Activations