© 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. 30717
    Prev
    Next
    INDEX
    Explanations

    statements that emphasize the act of pointing out or highlighting information

    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
    373
    +0.10
    0.5%
    246
    +0.09
    0.4%
    531
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.10
    0.03
    693
    +0.09
    0.03
    580
    +0.09
    0.03
    Negative Logits
     seiz
    -0.82
     ILCS
    -0.76
    anny
    -0.73
    kill
    -0.73
    anya
    -0.68
    miah
    -0.65
    dies
    -0.64
    ÃŃa
    -0.63
    terness
    -0.62
    lite
    -0.62
    POSITIVE LOGITS
     fingers
    1.00
     finger
    0.84
     strongly
    0.83
     towards
    0.81
     toward
    0.81
     decisively
    0.76
     cred
    0.73
     specifically
    0.73
     us
    0.72
     blame
    0.70
    Activations Density 0.262%

    No Known Activations