© 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. 4454
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or evaluations about situations or subjects

    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
    218
    +0.12
    0.6%
    389
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.12
    0.06
    519
    +0.12
    0.05
    55
    +0.11
    0.05
    Negative Logits
    actionDate
    -0.82
    lict
    -0.78
    licted
    -0.74
    umerable
    -0.70
    anwhile
    -0.70
     resided
    -0.69
     "$:/
    -0.68
    xtap
    -0.67
    ovember
    -0.66
    Ń·
    -0.66
    POSITIVE LOGITS
     hilarious
    0.90
     funny
    0.85
     adorable
    0.78
     delicious
    0.78
     sarc
    0.74
     ridiculous
    0.73
     delightful
    0.71
     amusing
    0.70
     rude
    0.69
     cute
    0.69
    Activations Density 0.223%

    No Known Activations