© 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. 31243
    Prev
    Next
    INDEX
    Explanations

    terms related to computing and file manipulation

    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
    737
    +0.12
    0.5%
    376
    +0.10
    0.5%
    510
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.08
    288
    +0.10
    0.19
    459
    +0.10
    0.02
    Negative Logits
    etheless
    -0.80
    theless
    -0.73
    amn
    -0.66
     meantime
    -0.66
    rawdownloadcloneembedreportprint
    -0.65
     meanwhile
    -0.64
    iblical
    -0.64
     furthermore
    -0.64
    utsu
    -0.63
     nonetheless
    -0.63
    POSITIVE LOGITS
    foo
    0.92
     Suppose
    0.90
     XY
    0.85
     foo
    0.82
     versus
    0.74
     Foo
    0.73
     might
    0.72
    example
    0.72
    ={
    0.69
    20439
    0.63
    Activations Density 6.860%

    No Known Activations