© 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. 4943
    Prev
    Next
    INDEX
    Explanations

    expressions of expectation or predictability

    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
    367
    +0.10
    0.4%
    355
    +0.09
    0.4%
    271
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.10
    0.03
    105
    +0.09
    0.03
    675
    +0.09
    0.03
    Negative Logits
    vertisement
    -0.78
    agra
    -0.76
    tex
    -0.73
    nan
    -0.70
    stein
    -0.67
    stocks
    -0.65
    wallet
    -0.64
    tha
    -0.64
     Rath
    -0.64
    burgh
    -0.63
    POSITIVE LOGITS
    LY
    0.82
    antly
    0.73
    ORY
    0.71
    icipated
    0.66
     bodily
    0.65
    ively
    0.65
    oice
    0.64
    orate
    0.64
    oric
    0.64
    lessly
    0.61
    Activations Density 0.072%

    No Known Activations