© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain formatting or spacing variations

    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
    +0.14
    0.6%
    213
    +0.12
    0.5%
    739
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.26
    426
    +0.12
    0.21
    107
    +0.10
    0.22
    Negative Logits
    glers
    -0.84
    orescence
    -0.73
    oresc
    -0.73
     Sail
    -0.72
    xual
    -0.71
     rooting
    -0.69
     bluff
    -0.69
    creen
    -0.69
    oaded
    -0.66
    ciating
    -0.64
    POSITIVE LOGITS
    0.98
    /
    0.92
    everyone
    0.88
    0.86
    Ð
    0.83
    Australia
    0.82
    âĢķ
    0.78
    Ö¼
    0.78
    align
    0.78
    Leaks
    0.78
    Activations Density 1.371%

    No Known Activations