© 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. 10-RES_POST_32K-OAI
    11. 29444
    Prev
    Next
    INDEX
    Explanations

    references to social media and digital platforms

    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
    144
    +0.13
    0.6%
    119
    +0.11
    0.5%
    533
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.13
    0.10
    143
    +0.11
    0.10
    550
    +0.11
    0.10
    Negative Logits
    usk
    -0.83
    hyde
    -0.66
    ÃĽ
    -0.64
    istle
    -0.63
    etary
    -0.63
    ī
    -0.63
    Gene
    -0.62
    zona
    -0.61
    clair
    -0.61
    oeuv
    -0.60
    POSITIVE LOGITS
     caus
    0.66
     grounding
    0.62
     noses
    0.59
     restraints
    0.58
     riot
    0.57
    tackle
    0.57
     transformative
    0.56
     constrained
    0.55
    ministic
    0.54
     doomed
    0.54
    Activations Density 0.433%

    No Known Activations