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

    Neuronpedia

    Jacobian LensNEW
    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. 6780
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in programming syntax

    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
    160
    +0.09
    0.4%
    437
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.09
    0.01
    699
    +0.09
    0.01
    284
    +0.09
    0.02
    Negative Logits
     Flavoring
    -0.80
     Mae
    -0.71
     Lowry
    -0.71
     Aviation
    -0.69
     TAMADRA
    -0.68
     Reese
    -0.67
     Vie
    -0.66
     Reloaded
    -0.65
    ITION
    -0.65
     Mechdragon
    -0.65
    POSITIVE LOGITS
    checked
    1.05
    require
    1.04
    license
    0.97
    label
    0.95
    help
    0.94
    cause
    0.92
    focus
    0.90
    breaker
    0.89
    named
    0.89
    root
    0.89
    Activations Density 0.091%

    No Known Activations