© 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. 10-RES_POST_32K-OAI
    11. 29403
    Prev
    Next
    INDEX
    Explanations

    references to PlayStation consoles and their model numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    725
    +0.09
    0.4%
    76
    +0.09
    0.4%
    356
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.09
    0.01
    343
    +0.09
    0.01
    595
    +0.09
    0.01
    Negative Logits
    butt
    -0.72
    ted
    -0.71
     rhy
    -0.66
     rh
    -0.65
     Hamm
    -0.63
     poppy
    -0.61
    ãĤ´
    -0.61
     corpor
    -0.60
     tong
    -0.60
    ascus
    -0.59
    POSITIVE LOGITS
     Vita
    1.08
    VR
    0.92
    Ħ¢
    0.91
    ĨĴ
    0.89
    VP
    0.85
    NI
    0.84
    4
    0.79
    »Ĵ
    0.78
     Move
    0.76
     Plus
    0.76
    Activations Density 0.096%

    No Known Activations