© 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. 27402
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly focusing on surnames

    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
    314
    +0.12
    0.6%
    119
    +0.10
    0.4%
    680
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.00
    439
    +0.10
    0.04
    406
    +0.10
    0.04
    Negative Logits
    hedral
    -0.81
    rament
    -0.78
    hered
    -0.67
     proble
    -0.65
    alore
    -0.64
    iling
    -0.60
    rocal
    -0.59
     misunder
    -0.59
    SourceFile
    -0.59
    urnal
    -0.59
    POSITIVE LOGITS
    ibrary
    1.19
    ounge
    1.12
    le
    1.10
    anguage
    1.08
    ands
    1.00
    ike
    0.96
    iberal
    0.95
    ittle
    0.92
    ogical
    0.89
    igible
    0.85
    Activations Density 0.364%

    No Known Activations