© 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. 8-RES_POST_32K-OAI
    11. 5168
    Prev
    Next
    INDEX
    Explanations

    instances of visibility or display actions, often in the context of media or user interface elements

    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
    373
    +0.13
    0.6%
    314
    +0.12
    0.6%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.01
    314
    +0.12
    -0.00
    651
    +0.11
    0.01
    Negative Logits
     pads
    -0.79
    romy
    -0.75
     warr
    -0.72
    bage
    -0.70
    nexus
    -0.70
     benches
    -0.68
    ells
    -0.67
     cones
    -0.63
    eele
    -0.63
    papers
    -0.62
    POSITIVE LOGITS
     Caption
    0.88
     Thumbnails
    0.74
    Case
    0.72
    ERROR
    0.71
    ¤
    0.68
     Transcript
    0.68
    Bah
    0.64
    ÙĪ
    0.64
    ģĸ
    0.64
    Related
    0.63
    Activations Density 0.054%

    No Known Activations