© 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 EvalsExportsAPI 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. 6287
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Mart" or related variations

    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
    314
    +0.13
    0.6%
    373
    +0.12
    0.5%
    444
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.13
    0.01
    444
    +0.12
    0.01
    621
    +0.12
    0.01
    Negative Logits
    clips
    -0.78
     Norn
    -0.69
    glers
    -0.66
     conce
    -0.65
    UTH
    -0.62
     eminent
    -0.59
     metals
    -0.58
     turb
    -0.58
    QUEST
    -0.58
     Cyprus
    -0.58
    POSITIVE LOGITS
    yrs
    1.39
    yr
    1.27
    ijn
    1.17
    ial
    1.14
    inelli
    1.13
    inez
    1.10
    ially
    1.09
    inal
    1.06
    ians
    1.03
    iate
    1.01
    Activations Density 0.047%

    No Known Activations