© 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. 5763
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational interactions

    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
    502
    +0.12
    0.6%
    661
    +0.10
    0.5%
    435
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.06
    354
    +0.10
    0.07
    566
    +0.10
    0.06
    Negative Logits
    obyl
    -0.94
    uably
    -0.81
    ĸļ
    -0.80
    htaking
    -0.78
    amous
    -0.74
    aeda
    -0.73
    assic
    -0.72
     Recession
    -0.68
     thri
    -0.68
    iferation
    -0.68
    POSITIVE LOGITS
     proceed
    0.92
     hurry
    0.85
     depart
    0.80
    ezvous
    0.79
     escort
    0.78
     haste
    0.78
     accompany
    0.78
     urgently
    0.76
    anwhile
    0.75
     rest
    0.74
    Activations Density 1.308%

    No Known Activations