© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4698
    Prev
    Next
    INDEX
    Explanations

    polling data and survey results related to public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    648
    +0.10
    0.4%
    150
    +0.09
    0.4%
    279
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.10
    0.05
    648
    +0.09
    0.05
    300
    +0.09
    0.05
    Negative Logits
    ensor
    -0.71
     coordinates
    -0.71
    alogue
    -0.69
     scales
    -0.67
    ses
    -0.66
    Pg
    -0.65
     logs
    -0.65
    eger
    -0.64
     levers
    -0.64
    alog
    -0.63
    POSITIVE LOGITS
     Americans
    0.83
     Britons
    0.79
     unmarried
    0.71
     challeng
    0.69
     millionaires
    0.65
     affluent
    0.64
     Californ
    0.64
     millennials
    0.64
     Millennials
    0.64
    piracy
    0.64
    Activations Density 0.763%

    No Known Activations