© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5593
    Prev
    Next
    INDEX
    Explanations

    references to games, libraries, and lists of items

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    420
    +0.12
    0.5%
    298
    +0.11
    0.5%
    508
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.06
    393
    +0.11
    0.04
    159
    +0.10
    0.03
    Negative Logits
    pmwiki
    -0.74
    irection
    -0.72
    ãĥĥãĥĪ
    -0.67
    azard
    -0.66
    adoes
    -0.66
    zeb
    -0.64
    soType
    -0.64
    actionDate
    -0.63
    adem
    -0.63
    Percent
    -0.62
    POSITIVE LOGITS
     mix
    1.09
     repertoire
    1.02
     equation
    1.00
     fray
    0.97
     arsenal
    0.86
     existing
    0.86
     already
    0.84
     reperto
    0.82
     coffers
    0.80
     list
    0.80
    Activations Density 0.299%

    No Known Activations