© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5788
    Prev
    Next
    INDEX
    Explanations

    references to participation and submission requirements in contests or events

    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
    558
    +0.10
    0.5%
    363
    +0.10
    0.5%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.10
    0.01
    510
    +0.10
    0.01
    550
    +0.09
    0.01
    Negative Logits
     arresting
    -0.81
     unnecess
    -0.71
     Notting
    -0.70
     successors
    -0.67
     accompan
    -0.67
     omission
    -0.66
     Nanto
    -0.66
     esc
    -0.65
    Reviewed
    -0.65
     digging
    -0.65
    POSITIVE LOGITS
    than
    0.83
    deg
    0.81
    oot
    0.76
    lear
    0.73
    Gam
    0.71
    uild
    0.70
    percent
    0.70
    wt
    0.69
    urrency
    0.69
    craft
    0.68
    Activations Density 0.118%

    No Known Activations