© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29599
    Prev
    Next
    INDEX
    Explanations

    metadata related to publication details, including dates and authors

    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
    +0.19
    0.9%
    497
    +0.11
    0.5%
    511
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.19
    0.03
    183
    +0.11
    0.02
    567
    +0.10
    0.01
    Negative Logits
     conclud
    -0.60
    KEN
    -0.59
    vous
    -0.58
     incent
    -0.58
    gans
    -0.58
     giveaways
    -0.58
     preached
    -0.57
     nipples
    -0.56
    hap
    -0.56
     indo
    -0.55
    POSITIVE LOGITS
    channelAvailability
    0.82
     thereto
    0.64
    geon
    0.63
    displayText
    0.62
    EngineDebug
    0.62
    cade
    0.61
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.60
    ART
    0.59
    BuyableInstoreAndOnline
    0.59
    straight
    0.57
    Activations Density 0.360%

    No Known Activations