© 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. 28647
    Prev
    Next
    INDEX
    Explanations

    rankings or positions within a competitive context

    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
    +0.12
    0.6%
    95
    +0.10
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.12
    0.04
    242
    +0.10
    0.04
    4
    +0.10
    0.04
    Negative Logits
     Patreon
    -0.76
    kens
    -0.65
    catentry
    -0.62
    æ©Ł
    -0.59
    ICO
    -0.59
    ITNESS
    -0.58
    Rules
    -0.58
    embed
    -0.58
     Simulator
    -0.57
    Attributes
    -0.57
    POSITIVE LOGITS
     place
    1.10
     nationally
    1.03
     among
    1.01
     overall
    1.00
     amongst
    0.94
    among
    0.87
     behind
    0.83
     quickest
    0.79
     globally
    0.77
     Place
    0.74
    Activations Density 0.273%

    No Known Activations