© 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. 4337
    Prev
    Next
    INDEX
    Explanations

    references to evidence or manifestation of concepts or ideas in various contexts

    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
    742
    +0.11
    0.5%
    171
    +0.11
    0.5%
    372
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.12
    362
    +0.11
    0.11
    393
    +0.11
    0.10
    Negative Logits
    itiz
    -0.69
     brakes
    -0.66
     Tycoon
    -0.65
     versa
    -0.65
     dunno
    -0.64
     WITHOUT
    -0.64
     bothered
    -0.63
     warr
    -0.63
    oided
    -0.62
     hadn
    -0.62
    POSITIVE LOGITS
    ECD
    0.71
     manifestations
    0.70
     evidenced
    0.69
     innumerable
    0.69
     examples
    0.69
     recent
    0.67
     performances
    0.67
     Fernand
    0.66
    Recent
    0.65
     writings
    0.65
    Activations Density 1.300%

    No Known Activations