© 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 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. 28672
    Prev
    Next
    INDEX
    Explanations

    quantitative assessments related to probabilities and statistics

    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
    702
    +0.12
    0.5%
    747
    +0.11
    0.5%
    286
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    702
    +0.12
    0.13
    747
    +0.11
    0.09
    156
    +0.09
    0.06
    Negative Logits
    APTER
    -0.93
    ĸļ
    -0.92
    æ©
    -0.87
     actionGroup
    -0.84
    Member
    -0.75
    Language
    -0.73
    gian
    -0.72
    english
    -0.71
    anga
    -0.70
    phabet
    -0.70
    POSITIVE LOGITS
     probabilities
    1.85
     probability
    1.78
     prediction
    1.70
     predictions
    1.60
     odds
    1.51
     Prediction
    1.48
     predict
    1.48
     predicting
    1.48
     likelihood
    1.43
     guesses
    1.35
    Activations Density 7.164%

    No Known Activations