© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5285
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting specific to web addresses and external links

    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
    +0.17
    0.8%
    557
    +0.15
    0.7%
    409
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.17
    0.04
    284
    +0.15
    0.04
    515
    +0.12
    0.03
    Negative Logits
     idle
    -0.66
     neutral
    -0.63
     milliseconds
    -0.63
     Chimera
    -0.62
     Infinity
    -0.61
     arithmetic
    -0.61
     Genius
    -0.60
     lowly
    -0.60
     equilibrium
    -0.60
     Leonardo
    -0.58
    POSITIVE LOGITS
    blogspot
    1.46
    wordpress
    1.31
    htm
    0.97
    tumblr
    0.94
    yahoo
    0.93
    info
    0.90
    blogs
    0.89
    html
    0.87
    bsite
    0.86
    files
    0.85
    Activations Density 0.171%

    No Known Activations