© 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. 8-RES_POST_32K-OAI
    11. 6330
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to food, humanitarian aid, and conflict situations

    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
    +0.15
    0.7%
    628
    +0.13
    0.6%
    696
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.17
    232
    +0.13
    0.14
    314
    +0.12
    0.02
    Negative Logits
     Robbins
    -0.84
     Hawth
    -0.79
     Berkshire
    -0.78
     Lovecraft
    -0.78
     Einstein
    -0.77
     Michaels
    -0.76
     Vaughn
    -0.73
     McH
    -0.72
     Hitch
    -0.71
     Grimm
    -0.71
    POSITIVE LOGITS
    etsk
    0.95
    anmar
    0.94
    intern
    0.93
    Syria
    0.92
    abwe
    0.91
     Gaddafi
    0.90
     hostages
    0.90
    alions
    0.90
    zbollah
    0.89
    angu
    0.88
    Activations Density 1.554%

    No Known Activations