© 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. 26850
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "it's," indicating a focus on statements and claims

    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
    687
    +0.11
    0.5%
    600
    +0.09
    0.4%
    287
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    522
    +0.11
    0.07
    55
    +0.09
    0.09
    208
    +0.09
    0.07
    Negative Logits
     illum
    -0.69
     accomp
    -0.68
    fixed
    -0.68
     discharged
    -0.65
    esm
    -0.65
     contrace
    -0.64
    Materials
    -0.64
    upon
    -0.63
    olded
    -0.63
     XD
    -0.63
    POSITIVE LOGITS
     unclear
    0.80
     worth
    0.75
     unsur
    0.74
    politics
    0.70
    prising
    0.68
    olicy
    0.67
     exaggeration
    0.67
    oday
    0.66
     hardly
    0.65
     fair
    0.64
    Activations Density 0.537%

    No Known Activations