© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 9130
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to personal experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    727
    +0.12
    0.6%
    683
    +0.12
    0.5%
    189
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.12
    0.10
    326
    +0.12
    0.24
    762
    +0.09
    0.19
    Negative Logits
     promoters
    -0.78
     exemptions
    -0.74
     Alpine
    -0.73
     museums
    -0.72
     charities
    -0.71
     tourism
    -0.71
     stadiums
    -0.69
     Disneyland
    -0.67
     coastal
    -0.67
     pilgrims
    -0.67
    POSITIVE LOGITS
    ername
    1.17
    /(
    1.16
    ?,
    1.11
    .?
    1.11
    ··
    1.04
     :=
    1.04
     =>
    1.03
    ...?
    1.03
     ->
    1.02
    >,
    1.01
    Activations Density 8.022%

    No Known Activations