© 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 EvalsExportsinterp-engineNEWAPI 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. 7635
    Prev
    Next
    INDEX
    Explanations

    names and references to specific documents or reports related to a subject

    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
    420
    +0.15
    0.7%
    496
    +0.12
    0.6%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.02
    158
    +0.12
    0.01
    514
    +0.12
    0.01
    Negative Logits
    OGR
    -0.76
    UNCH
    -0.69
    izontal
    -0.69
    FORE
    -0.69
     Compass
    -0.65
     Inqu
    -0.64
    izons
    -0.64
     Tinder
    -0.62
    oad
    -0.62
    olor
    -0.61
    POSITIVE LOGITS
    ilt
    0.84
    addons
    0.72
    seq
    0.72
    lette
    0.71
    raid
    0.70
    Xi
    0.70
    ler
    0.70
    bard
    0.70
    gerald
    0.69
    els
    0.69
    Activations Density 0.093%

    No Known Activations