© 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. 29368
    Prev
    Next
    INDEX
    Explanations

    specific types of metadata and numerical information related to films

    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
    176
    +0.16
    0.8%
    373
    +0.15
    0.7%
    316
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.03
    314
    +0.15
    -0.00
    176
    +0.11
    0.01
    Negative Logits
    gypt
    -0.80
    ï¸
    -0.78
     ISBN
    -0.76
    uay
    -0.74
    ="#
    -0.74
    heit
    -0.73
    psey
    -0.72
    !/
    -0.72
    DragonMagazine
    -0.70
    iliar
    -0.70
    POSITIVE LOGITS
    pixel
    0.75
     Adinida
    0.74
    ©¶æ¥µ
    0.69
     TheNitromeFan
    0.66
    udeb
    0.65
     SolidGoldMagikarp
    0.61
     davidjl
    0.60
    broad
    0.59
    andre
    0.59
    username
    0.58
    Activations Density 0.135%

    No Known Activations