© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    percentage values and related data expressions

    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
    324
    +0.10
    0.5%
    595
    +0.10
    0.4%
    214
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.10
    0.21
    23
    +0.10
    0.20
    426
    +0.10
    0.17
    Negative Logits
    Zip
    -0.68
     Guinness
    -0.67
    STAR
    -0.64
    å£
    -0.62
    yip
    -0.62
    oteric
    -0.60
    trade
    -0.60
    olean
    -0.59
    IDENT
    -0.58
    bnb
    -0.57
    POSITIVE LOGITS
    apers
    0.86
    ©¶æ
    0.80
    Ħ¢
    0.76
     incor
    0.76
    lete
    0.72
    /
    0.69
    âģ
    0.68
    aper
    0.65
    ĵĺ
    0.65
    IJ
    0.65
    Activations Density 0.842%

    No Known Activations