© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    actions involving raising, lifting, or positioning

    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
    25
    +0.12
    0.6%
    373
    +0.10
    0.5%
    514
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.03
    435
    +0.10
    0.02
    555
    +0.09
    0.03
    Negative Logits
    ombat
    -0.66
    iliate
    -0.59
    wik
    -0.57
    irus
    -0.57
    CCC
    -0.57
     Train
    -0.56
    acci
    -0.56
    inator
    -0.56
     Diseases
    -0.55
     stereotype
    -0.55
    POSITIVE LOGITS
    raised
    0.93
     eyebrow
    0.83
     brow
    0.82
     eyebrows
    0.82
    handed
    0.74
     tilted
    0.70
     fists
    0.69
     loft
    0.67
     stakes
    0.67
    hands
    0.67
    Activations Density 0.219%

    No Known Activations