© 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. 7548
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knock" and its variations

    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
    373
    +0.12
    0.5%
    96
    +0.10
    0.5%
    168
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.12
    0.03
    526
    +0.10
    0.00
    96
    +0.10
    0.02
    Negative Logits
    trial
    -0.70
    batch
    -0.66
    utan
    -0.61
    cano
    -0.60
    lus
    -0.60
    cean
    -0.60
    oleon
    -0.57
    UAL
    -0.57
    vity
    -0.57
     Leopard
    -0.57
    POSITIVE LOGITS
     doors
    1.14
     door
    0.92
     wood
    0.87
     gates
    0.79
     walls
    0.75
     Door
    0.73
     bushes
    0.73
     Doors
    0.69
    door
    0.68
     windows
    0.68
    Activations Density 0.179%

    No Known Activations