© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    actions and interactions during social gatherings

    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
    560
    +0.13
    0.6%
    714
    +0.11
    0.5%
    157
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.13
    0.06
    70
    +0.11
    0.08
    271
    +0.10
    0.05
    Negative Logits
     Creator
    -0.68
     Founding
    -0.58
    tains
    -0.58
     Rhino
    -0.57
    20439
    -0.56
     Buffer
    -0.55
     Dating
    -0.55
    inosaur
    -0.54
     ().
    -0.53
    pecially
    -0.53
    POSITIVE LOGITS
     slowly
    1.03
    yss
    0.94
     awhile
    0.89
     hesitated
    0.86
     cautiously
    0.85
     grate
    0.84
     gradually
    0.84
     aback
    0.81
     nearer
    0.78
     reluctantly
    0.78
    Activations Density 0.871%

    No Known Activations