© 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. 29511
    Prev
    Next
    INDEX
    Explanations

    connections between statistical analysis and societal issues

    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
    432
    +0.12
    0.5%
    527
    +0.11
    0.5%
    63
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.34
    401
    +0.11
    0.26
    594
    +0.10
    0.19
    Negative Logits
    Russ
    -0.55
    ãĥķãĤ¡
    -0.54
    ÃįÃį
    -0.54
    ullivan
    -0.53
     newcom
    -0.52
    nants
    -0.50
    senal
    -0.50
    plet
    -0.49
    Dispatch
    -0.49
    »
    -0.48
    POSITIVE LOGITS
     is
    1.93
     involves
    1.82
     has
    1.81
     depends
    1.78
     seems
    1.77
     differs
    1.77
     appears
    1.76
     tends
    1.76
     represents
    1.75
     requires
    1.74
    Activations Density 10.922%

    No Known Activations