© 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. 28165
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Kar" or related references to individuals with that name

    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
    145
    +0.13
    0.6%
    659
    +0.13
    0.6%
    741
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    145
    +0.13
    0.01
    741
    +0.11
    0.01
    Negative Logits
    CRIP
    -0.70
     NX
    -0.65
    IBLE
    -0.63
    cript
    -0.62
     agents
    -0.62
     Malf
    -0.61
     lett
    -0.61
     Furious
    -0.59
     aloud
    -0.59
     Merry
    -0.58
    POSITIVE LOGITS
    amaz
    1.21
    olina
    1.15
    sten
    1.10
    zai
    1.07
    isma
    1.07
    acan
    1.05
    thus
    0.94
    bon
    0.94
    olyn
    0.93
    imov
    0.92
    Activations Density 0.038%

    No Known Activations