© 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. 10-RES_POST_32K-OAI
    6. 29427
    Prev
    Next
    INDEX
    Explanations

    statements regarding product specifications and performance descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    292
    +0.10
    0.4%
    339
    +0.09
    0.4%
    671
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.10
    102
    +0.09
    0.10
    566
    +0.09
    0.08
    Negative Logits
    pmwiki
    -0.83
     Flavoring
    -0.79
     transcripts
    -0.76
    bart
    -0.71
    ROR
    -0.70
     Eps
    -0.70
    lies
    -0.69
    mens
    -0.69
    ebin
    -0.69
    pedia
    -0.67
    POSITIVE LOGITS
     equipped
    1.35
     powered
    1.25
     sleek
    1.15
     fitted
    1.12
     priced
    1.11
     rugged
    1.05
     marketed
    1.05
    equipped
    1.05
     capable
    1.03
    powered
    1.01
    Activations Density 0.717%

    No Known Activations