© 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. 6092
    Prev
    Next
    INDEX
    Explanations

    references to parts or remnants of larger entities

    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
    506
    +0.12
    0.5%
    218
    +0.10
    0.5%
    229
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.09
    608
    +0.10
    0.08
    669
    +0.10
    0.06
    Negative Logits
    amazon
    -0.74
    xtap
    -0.74
    weed
    -0.73
    æ©Ł
    -0.71
    FIG
    -0.70
    Press
    -0.70
    Bound
    -0.69
    twitch
    -0.68
    alert
    -0.68
    oking
    -0.68
    POSITIVE LOGITS
     deceased
    0.86
     childhood
    0.78
     defunct
    0.77
     civilization
    0.75
     civilisation
    0.74
     murdered
    0.72
     mankind
    0.71
     slain
    0.71
     humanity
    0.70
     Childhood
    0.69
    Activations Density 0.629%

    No Known Activations