© 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. 5378
    Prev
    Next
    INDEX
    Explanations

    references to notable performances in sports or competitions

    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
    540
    +0.16
    0.7%
    761
    +0.10
    0.5%
    668
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.16
    0.10
    274
    +0.10
    0.05
    531
    +0.10
    0.06
    Negative Logits
    bard
    -0.67
     sclerosis
    -0.64
     knots
    -0.62
     solutions
    -0.62
     consortium
    -0.61
     encyclopedia
    -0.60
    conservancy
    -0.58
     Solution
    -0.58
     solution
    -0.58
    bidden
    -0.57
    POSITIVE LOGITS
    luster
    0.79
    Against
    0.79
    ufact
    0.77
    aries
    0.77
     domestically
    0.75
     Incarn
    0.73
     abroad
    0.73
    lust
    0.73
     against
    0.73
     elsewhere
    0.72
    Activations Density 0.568%

    No Known Activations