© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    references to potential and its implications in various contexts

    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
    712
    +0.09
    0.4%
    151
    +0.08
    0.4%
    154
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    413
    +0.09
    0.02
    451
    +0.08
    0.02
    712
    +0.08
    0.01
    Negative Logits
    ĪĴ
    -0.83
    cise
    -0.64
    tein
    -0.63
     Claus
    -0.62
    rarily
    -0.61
    fin
    -0.60
    FactoryReloaded
    -0.60
     Fever
    -0.60
    phia
    -0.60
     bras
    -0.59
    POSITIVE LOGITS
    ities
    1.30
    ity
    1.04
     pitfalls
    0.93
    iary
    0.81
    itri
    0.76
    ITY
    0.75
    rawdownloadcloneembedreportprint
    0.74
     adversaries
    0.74
     usefulness
    0.74
    paren
    0.73
    Activations Density 0.110%

    No Known Activations