© 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. 27413
    Prev
    Next
    INDEX
    Explanations

    specific legal and political references related to rights and legislation

    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
    +0.14
    0.6%
    651
    +0.11
    0.5%
    97
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.00
    374
    +0.11
    -0.01
    12
    +0.11
    0.07
    Negative Logits
    ĸļ
    -0.88
    itars
    -0.84
    rawdownloadcloneembedreportprint
    -0.84
    hement
    -0.83
    duino
    -0.75
    riott
    -0.70
    ahime
    -0.69
    avorite
    -0.67
    ategory
    -0.66
     separat
    -0.65
    POSITIVE LOGITS
    ¼
    0.90
    ³
    0.90
    ·
    0.84
    ½
    0.83
    ĩ
    0.82
    ¶
    0.79
    ª
    0.78
    °
    0.76
    ĺ
    0.76
    ©
    0.74
    Activations Density 1.919%

    No Known Activations