© 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. 31359
    Prev
    Next
    INDEX
    Explanations

    references to specific stories, information, updates, or features related to products and news

    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
    364
    +0.11
    0.5%
    276
    +0.10
    0.5%
    534
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.11
    0.06
    258
    +0.10
    0.06
    229
    +0.09
    0.05
    Negative Logits
    ELD
    -0.65
    pires
    -0.64
    lihood
    -0.63
    SpaceEngineers
    -0.63
    ilion
    -0.58
    umerable
    -0.58
    judicial
    -0.57
     affirmed
    -0.57
    ¶ħ
    -0.57
    illus
    -0.56
    POSITIVE LOGITS
     click
    1.53
     check
    1.49
     visit
    1.45
     please
    1.39
     see
    1.39
     CLICK
    1.38
     try
    1.34
     consult
    1.33
     refer
    1.33
     go
    1.32
    Activations Density 0.650%

    No Known Activations