© 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. 5314
    Prev
    Next
    INDEX
    Explanations

    references to authors and studies in academic literature

    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
    +0.15
    0.7%
    363
    +0.12
    0.6%
    625
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.12
    232
    +0.12
    0.07
    314
    +0.10
    0.01
    Negative Logits
    Greek
    -0.70
    000000
    -0.67
     Timeline
    -0.63
     Gemini
    -0.62
    /)
    -0.62
    cape
    -0.61
     =================================================================
    -0.61
     POV
    -0.60
     Modified
    -0.59
     Possibly
    -0.58
    POSITIVE LOGITS
    izoph
    0.70
    gem
    0.65
    atson
    0.64
    arton
    0.64
    ullivan
    0.62
    rentice
    0.62
    aples
    0.60
    isch
    0.60
    aunders
    0.59
    essing
    0.59
    Activations Density 0.370%

    No Known Activations