© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    instances of the word "another"

    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
    +0.20
    0.7%
    159
    +0.15
    0.5%
    709
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.20
    0.07
    223
    +0.15
    0.07
    402
    +0.14
    0.05
    Negative Logits
    liest
    -1.16
    ouls
    -0.96
    alties
    -0.96
    oes
    -0.89
    hips
    -0.88
    lee
    -0.87
    Always
    -0.87
    Lee
    -0.87
    Cu
    -0.86
     Presence
    -0.85
    POSITIVE LOGITS
    worldly
    1.72
     dimension
    1.27
     notch
    1.18
     unnamed
    1.12
     unidentified
    1.08
     major
    1.06
     batch
    1.04
    wcs
    1.03
    ļéĨĴ
    1.02
     layer
    1.00
    Activations Density 1.304%

    No Known Activations