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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4800
    Prev
    Next
    INDEX
    Explanations

    references to sections, issues, or identifiers in formal documents or articles

    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
    373
    +0.14
    0.7%
    233
    +0.11
    0.5%
    412
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.01
    699
    +0.11
    0.01
    435
    +0.10
    0.01
    Negative Logits
    ngth
    -0.88
    erv
    -0.78
    heit
    -0.78
    aspers
    -0.76
    ritz
    -0.76
    vantage
    -0.74
    artisan
    -0.71
    erm
    -0.71
    avascript
    -0.71
    mble
    -0.70
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.70
    channelAvailability
    0.69
     latest
    0.69
    displayText
    0.65
     Runtime
    0.64
     sleeves
    0.63
     overr
    0.61
     amended
    0.61
     seq
    0.61
     revised
    0.59
    Activations Density 0.041%

    No Known Activations