© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6044
    Prev
    Next
    INDEX
    Explanations

    sequences of hyphens or dashes used in formatting

    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
    347
    +0.12
    0.5%
    308
    +0.11
    0.5%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.12
    0.02
    727
    +0.11
    0.02
    290
    +0.09
    0.02
    Negative Logits
    sters
    -0.74
    issance
    -0.73
    teenth
    -0.68
    ORPG
    -0.68
    ffield
    -0.65
    mares
    -0.62
     enthusi
    -0.61
    ories
    -0.59
    ory
    -0.59
    iths
    -0.58
    POSITIVE LOGITS
    help
    1.02
    enable
    0.99
    sil
    0.98
    disable
    0.96
    iframe
    0.95
    [[
    0.85
    dry
    0.83
    output
    0.83
    gpu
    0.82
    global
    0.81
    Activations Density 0.106%

    No Known Activations