© 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. 10-RES_POST_32K-OAI
    11. 29407
    Prev
    Next
    INDEX
    Explanations

    references to industry influence on health and nutrition

    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
    373
    +0.45
    2.8%
    481
    +0.20
    1.2%
    326
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.45
    -0.16
    288
    +0.20
    0.43
    659
    +0.14
    0.15
    Negative Logits
     Canaver
    -0.63
    etheless
    -0.63
     Allaah
    -0.61
    CVE
    -0.59
    ?ãĢį
    -0.58
    DragonMagazine
    -0.58
     Mulcair
    -0.56
     Zoro
    -0.56
     Rohing
    -0.55
    )))
    -0.55
    POSITIVE LOGITS
    rehensive
    0.45
    ÃĥÃĤ
    0.42
    Ý
    0.42
    isSpecial
    0.42
     pione
    0.42
    \\\\\\\\
    0.42
     externalTo
    0.41
    StreamerBot
    0.41
    akable
    0.40
    ActionCode
    0.40
    Activations Density 28.563%

    No Known Activations