© 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. 31591
    Prev
    Next
    INDEX
    Explanations

    references to the music genre "dub" and associated terms, as well as specific names related to "Dub" and contributors in that context

    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
    326
    +0.14
    0.7%
    211
    +0.13
    0.6%
    183
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.03
    659
    +0.13
    0.02
    326
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.77
     Hera
    -0.63
     Sins
    -0.63
     Galile
    -0.62
     Holmes
    -0.61
     actionGroup
    -0.60
    FTWARE
    -0.60
    atem
    -0.60
    anders
    -0.60
     unpre
    -0.59
    POSITIVE LOGITS
    step
    1.26
    rov
    1.10
    bing
    1.09
    plates
    1.01
    bed
    0.98
    sonian
    0.98
    ois
    0.97
    iously
    0.94
    ious
    0.90
    liner
    0.87
    Activations Density 0.180%

    No Known Activations