© 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 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. 30790
    Prev
    Next
    INDEX
    Explanations

    names and references related to the entertainment and media industry

    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
    314
    +0.17
    0.8%
    2
    +0.12
    0.6%
    334
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.11
    232
    +0.12
    0.09
    314
    +0.12
    -0.01
    Negative Logits
     captcha
    -0.78
     handgun
    -0.70
     socket
    -0.69
     spelling
    -0.68
     process
    -0.68
     tune
    -0.67
     typing
    -0.66
     cigar
    -0.66
     manuscript
    -0.65
     flatt
    -0.65
    POSITIVE LOGITS
    Week
    1.09
     Matters
    1.00
    Aid
    0.99
    Gate
    0.97
    Hub
    0.97
     Digest
    0.96
    Scene
    0.95
    Night
    0.94
     Week
    0.94
     Depot
    0.91
    Activations Density 1.408%

    No Known Activations