© 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. 10-RES_POST_32K-OAI
    11. 27210
    Prev
    Next
    INDEX
    Explanations

    references to news organizations and their content distribution

    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
    373
    +0.18
    0.8%
    684
    +0.09
    0.4%
    386
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.18
    0.07
    352
    +0.09
    0.08
    254
    +0.09
    0.07
    Negative Logits
    gypt
    -0.77
     reluct
    -0.74
    raid
    -0.73
    rez
    -0.69
    ibaba
    -0.68
    è¦ļéĨĴ
    -0.67
    habi
    -0.67
    adal
    -0.67
    asin
    -0.66
    ebin
    -0.65
    POSITIVE LOGITS
     Comedy
    0.80
     Shakespeare
    0.74
     Notting
    0.74
     Preston
    0.73
    issance
    0.73
     sax
    0.72
     Liverpool
    0.71
     sculpture
    0.70
     comedians
    0.69
     entertain
    0.69
    Activations Density 0.187%

    No Known Activations