© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    numbers or measurements related to distance or extent

    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
    195
    +0.20
    0.6%
    288
    +0.19
    0.6%
    99
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.06
    99
    +0.19
    0.04
    596
    +0.18
    0.04
    Negative Logits
    rics
    -1.06
     hoc
    -1.03
    elta
    -1.02
    der
    -0.99
    nai
    -0.97
    mit
    -0.96
    jiang
    -0.95
    Fe
    -0.94
    WN
    -0.92
    äºĶ
    -0.90
    POSITIVE LOGITS
    finder
    1.77
     Rover
    1.54
    range
    1.30
     ranges
    1.27
    ahead
    1.25
     range
    1.18
    ranging
    1.12
    enegger
    1.05
     Range
    1.01
    ollah
    1.00
    Activations Density 0.793%

    No Known Activations