© 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. 10284
    Prev
    Next
    INDEX
    Explanations

    information related to a variety of topics, including scientific research, academic salaries, vehicle regulations, survey results, and genetic compatibility based on smell

    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
    +0.19
    0.7%
    714
    +0.11
    0.4%
    608
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.15
    608
    +0.11
    0.12
    362
    +0.11
    0.08
    Negative Logits
    å§
    -1.02
    oki
    -0.96
    jam
    -0.96
    wash
    -0.96
    REAM
    -0.91
    ãĤ¸
    -0.91
    rek
    -0.89
    KK
    -0.87
    roo
    -0.87
    etsk
    -0.87
    POSITIVE LOGITS
     geography
    1.32
     demographics
    1.30
     severity
    1.26
     preferences
    1.24
     differing
    1.22
     varying
    1.19
     individual
    1.18
     ethnicity
    1.16
     idiosyncr
    1.15
     gender
    1.14
    Activations Density 2.915%

    No Known Activations