© 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. 5507
    Prev
    Next
    INDEX
    Explanations

    command line instructions and syntax related to file and system operations

    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
    284
    +0.11
    0.5%
    438
    +0.10
    0.4%
    127
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.04
    289
    +0.10
    0.01
    314
    +0.09
    -0.00
    Negative Logits
    icz
    -0.64
    rush
    -0.63
     Excellence
    -0.63
     Tune
    -0.63
     issuer
    -0.63
     sacrific
    -0.61
     Gamble
    -0.59
     Zeus
    -0.59
    ais
    -0.59
    erald
    -0.59
    POSITIVE LOGITS
    cess
    0.83
    loo
    0.83
    usb
    0.77
    conn
    0.72
    levels
    0.70
    mouth
    0.68
    bors
    0.67
    alties
    0.65
    itude
    0.64
    times
    0.64
    Activations Density 0.171%

    No Known Activations