© 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. 10432
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and technical topics

    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
    288
    +0.16
    0.8%
    367
    +0.11
    0.6%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.39
    481
    +0.11
    0.29
    367
    +0.10
    0.19
    Negative Logits
    arger
    -0.71
     UNCLASSIFIED
    -0.67
     reper
    -0.61
     ster
    -0.60
    obbies
    -0.59
    ople
    -0.58
     LM
    -0.58
    clip
    -0.57
    velt
    -0.56
    é¾įå
    -0.55
    POSITIVE LOGITS
     âĢº
    0.66
     âĢİ
    0.64
    umbai
    0.56
    utterstock
    0.56
     cryptocurrency
    0.56
    brate
    0.54
     Donald
    0.53
    Skip
    0.53
     Belfast
    0.52
     Posted
    0.52
    Activations Density 12.370%

    No Known Activations