© 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. 8-RES_POST_32K-OAI
    11. 8559
    Prev
    Next
    INDEX
    Explanations

    terms related to adulthood or maturation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    752
    +0.09
    0.4%
    284
    +0.09
    0.4%
    104
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.03
    728
    +0.09
    0.01
    314
    +0.09
    -0.00
    Negative Logits
    é¾įå¥ij士
    -0.68
    EStreamFrame
    -0.67
     Kuala
    -0.65
     Languages
    -0.65
    anguage
    -0.64
     luck
    -0.64
    ingu
    -0.63
     poems
    -0.62
     Kamp
    -0.62
    ĺħ
    -0.62
    POSITIVE LOGITS
    ups
    0.95
    ry
    0.93
    zeb
    0.77
    ervatives
    0.74
    ibility
    0.69
     ups
    0.69
    up
    0.69
    iott
    0.68
    ild
    0.68
    etime
    0.67
    Activations Density 0.195%

    No Known Activations