© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    instances of specific non-English characters or symbols

    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
    373
    +0.12
    0.6%
    531
    +0.11
    0.5%
    216
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.01
    136
    +0.11
    0.01
    591
    +0.10
    0.01
    Negative Logits
    unct
    -0.79
    ulators
    -0.79
    iture
    -0.76
     Ceres
    -0.75
    ographically
    -0.72
     Shutdown
    -0.69
    ilities
    -0.67
    ierrez
    -0.67
     board
    -0.67
    uncture
    -0.67
    POSITIVE LOGITS
    ¹
    1.41
    ¨
    1.35
    £
    1.31
    ±
    1.29
    ³
    1.22
    ª
    1.20
    Ń
    1.16
    ¯
    1.12
    º
    1.08
    ·
    1.06
    Activations Density 0.017%

    No Known Activations