© 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. 10-RES_POST_32K-OAI
    11. 30895
    Prev
    Next
    INDEX
    Explanations

    aspects related to product details and customization options

    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
    109
    +0.13
    0.6%
    467
    +0.11
    0.5%
    599
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.22
    640
    +0.11
    0.18
    145
    +0.10
    0.15
    Negative Logits
     WATCHED
    -0.88
    externalActionCode
    -0.87
    DEN
    -0.74
    Downloadha
    -0.74
    channelAvailability
    -0.74
    Increased
    -0.71
    CVE
    -0.71
    EStreamFrame
    -0.70
     Lauder
    -0.68
    ASHINGTON
    -0.68
    POSITIVE LOGITS
    Basically
    0.83
     Basically
    0.82
     nifty
    0.73
     vo
    0.73
    Setup
    0.72
     depending
    0.71
     setup
    0.70
     optionally
    0.70
    Each
    0.69
     customizable
    0.69
    Activations Density 1.990%

    No Known Activations