© 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. 2892
    Prev
    Next
    INDEX
    Explanations

    information related to current events, including political, environmental, and social issues

    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
    325
    +0.16
    0.5%
    386
    +0.15
    0.5%
    121
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.16
    0.03
    386
    +0.15
    0.02
    559
    +0.14
    0.02
    Negative Logits
    rency
    -1.31
    oven
    -1.24
    nesia
    -1.21
    cius
    -1.10
    inki
    -1.06
    atos
    -1.02
    ushi
    -0.97
    omsky
    -0.96
    ullivan
    -0.96
    ĪĴ
    -0.96
    POSITIVE LOGITS
     Getty
    1.27
     SPL
    1.24
     AFP
    1.15
     ©
    1.15
     Misty
    1.07
     EPA
    1.06
     Suzanne
    1.04
     Gazette
    1.03
     Lance
    1.03
     Provided
    1.02
    Activations Density 0.046%

    No Known Activations