© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 31590
    Prev
    Next
    INDEX
    Explanations

    references to player statistics and achievements in sports

    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
    75
    +0.13
    0.6%
    341
    +0.11
    0.5%
    454
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.13
    0.04
    147
    +0.11
    0.04
    121
    +0.10
    0.04
    Negative Logits
    kefeller
    -0.67
    yll
    -0.66
    fo
    -0.65
     Engels
    -0.65
     boils
    -0.61
    acea
    -0.61
     secretaries
    -0.61
    minist
    -0.60
    INESS
    -0.59
    ollah
    -0.59
    POSITIVE LOGITS
     who
    1.08
    who
    1.06
     whom
    0.97
     waivers
    0.91
     sidelined
    0.90
    whose
    0.89
     undrafted
    0.87
     whose
    0.85
     rookie
    0.84
     meanwhile
    0.82
    Activations Density 0.329%

    No Known Activations