© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and identifiers in software or engineering contexts

    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
    766
    +0.10
    0.5%
    230
    +0.10
    0.4%
    565
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.10
    0.01
    284
    +0.10
    0.01
    192
    +0.10
    0.01
    Negative Logits
     Magnum
    -0.74
     Twist
    -0.70
     Cutter
    -0.67
     XY
    -0.67
     Candle
    -0.67
     Enabled
    -0.66
     Seal
    -0.66
     Advertisement
    -0.66
     Trial
    -0.66
     Wax
    -0.65
    POSITIVE LOGITS
    iverpool
    0.92
    ansas
    0.91
    sburgh
    0.86
    ondon
    0.85
    ","
    0.84
    incinnati
    0.84
    "},{"
    0.83
    icago
    0.82
    addons
    0.82
    ricanes
    0.80
    Activations Density 0.028%

    No Known Activations