© 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. 10-RES_POST_32K-OAI
    11. 28303
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associated teams or affiliations

    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
    378
    +0.12
    0.5%
    38
    +0.11
    0.5%
    558
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.18
    232
    +0.11
    0.13
    314
    +0.11
    -0.00
    Negative Logits
     Mayweather
    -0.97
     Chavez
    -0.89
     Zimbabwe
    -0.89
     Caesar
    -0.83
     Bengals
    -0.81
     Cincinnati
    -0.80
     Crane
    -0.78
     CPC
    -0.75
     Cavs
    -0.75
     Cavaliers
    -0.75
    POSITIVE LOGITS
    å
    1.82
     Stockholm
    1.51
     Bj
    1.48
     Swedish
    1.48
    ø
    1.47
     Anders
    1.46
    riks
    1.45
     Sweden
    1.45
    ansson
    1.45
     Swed
    1.41
    Activations Density 2.029%

    No Known Activations