© 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. 29038
    Prev
    Next
    INDEX
    Explanations

    complex data structures and symbolic representations in the context of programming or mathematical expressions

    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
    316
    +0.12
    0.6%
    512
    +0.11
    0.5%
    62
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.04
    289
    +0.11
    0.02
    699
    +0.10
    0.03
    Negative Logits
    Sov
    -0.81
    Versions
    -0.71
     unden
    -0.70
     pestic
    -0.67
     behavi
    -0.65
    phony
    -0.65
    maxwell
    -0.65
     sovere
    -0.65
    SPONSORED
    -0.65
     eleph
    -0.63
    POSITIVE LOGITS
     227
    0.86
     429
    0.86
    76561
    0.85
     328
    0.83
     255
    0.83
     0
    0.83
     229
    0.82
     [-
    0.81
     226
    0.79
    minecraft
    0.79
    Activations Density 0.244%

    No Known Activations