© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    web links and online resource references

    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
    186
    +0.10
    0.4%
    705
    +0.09
    0.4%
    559
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.10
    0.03
    680
    +0.09
    0.02
    114
    +0.09
    0.02
    Negative Logits
    -+-+
    -0.78
    terness
    -0.77
     destro
    -0.74
    luster
    -0.74
    ĪĴ
    -0.71
    lehem
    -0.70
     eleph
    -0.70
     neighb
    -0.68
    uton
    -0.68
     subur
    -0.68
    POSITIVE LOGITS
    sites
    0.74
    api
    0.70
    events
    0.67
    Vote
    0.65
    uploads
    0.65
    wp
    0.65
     Presents
    0.64
    youtu
    0.64
    :/
    0.62
    cms
    0.61
    Activations Density 0.177%

    No Known Activations