© 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. 7094
    Prev
    Next
    INDEX
    Explanations

    terms related to official titles or roles in communication contexts

    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
    +0.14
    0.6%
    145
    +0.12
    0.5%
    21
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.14
    0.04
    679
    +0.12
    0.05
    21
    +0.10
    0.04
    Negative Logits
    APTER
    -0.77
    oshenko
    -0.62
     sailors
    -0.61
    pmwiki
    -0.61
     dominance
    -0.60
     favour
    -0.59
    TIT
    -0.59
    keepers
    -0.59
    ateurs
    -0.58
     critics
    -0.57
    POSITIVE LOGITS
    points
    0.70
     Bayer
    0.69
     MTA
    0.62
    eah
    0.60
    point
    0.59
     elaborated
    0.58
    alyst
    0.57
    ector
    0.57
    olics
    0.57
    zona
    0.57
    Activations Density 0.282%

    No Known Activations