© 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. 4527
    Prev
    Next
    INDEX
    Explanations

    elements related to visual content and notifications

    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
    115
    +0.10
    0.4%
    756
    +0.08
    0.4%
    584
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    477
    +0.08
    0.01
    183
    +0.08
    0.01
    Negative Logits
     Morrow
    -0.68
    oute
    -0.68
    Deal
    -0.67
     UM
    -0.66
     Commit
    -0.63
    Fax
    -0.62
     FW
    -0.61
    rous
    -0.60
    FTWARE
    -0.60
    uana
    -0.59
    POSITIVE LOGITS
    URES
    0.79
     Sketch
    0.74
    redients
    0.73
     cartoons
    0.70
    è£ħ
    0.68
    uador
    0.67
    Shape
    0.67
     Thumbnails
    0.65
    picture
    0.64
     centre
    0.64
    Activations Density 0.052%

    No Known Activations