© 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. 10-RES_POST_32K-OAI
    11. 31794
    Prev
    Next
    INDEX
    Explanations

    versioning and release information related to published materials

    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
    326
    +0.11
    0.5%
    493
    +0.09
    0.4%
    356
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.11
    0.05
    306
    +0.09
    0.05
    707
    +0.08
    0.04
    Negative Logits
     laughter
    -0.71
     Antar
    -0.71
    nesota
    -0.70
     athlet
    -0.66
     NAACP
    -0.65
     metaphors
    -0.65
     glim
    -0.64
    itement
    -0.64
     vividly
    -0.64
    iris
    -0.64
    POSITIVE LOGITS
     Updated
    1.16
     Added
    1.09
     Version
    1.07
    Added
    1.02
     Update
    1.01
     Changed
    1.00
    Updated
    0.99
     Fixed
    0.95
    Version
    0.94
     update
    0.93
    Activations Density 0.669%

    No Known Activations