© 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 EvalsExportsinterp-engineNEWAPI 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. 27702
    Prev
    Next
    INDEX
    Explanations

    references to universities and incidents related to them

    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
    410
    +0.11
    0.5%
    436
    +0.11
    0.5%
    319
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.11
    0.08
    540
    +0.11
    0.10
    436
    +0.10
    0.05
    Negative Logits
    roup
    -0.72
     toget
    -0.67
     Ended
    -0.67
    lihood
    -0.62
    roxy
    -0.58
     comr
    -0.56
    æĪ¦
    -0.55
    issions
    -0.55
    jug
    -0.55
    eni
    -0.54
    POSITIVE LOGITS
     example
    1.53
     exception
    1.50
     examples
    1.37
    example
    1.32
     exempl
    1.11
    Example
    1.11
     exceptions
    1.10
     instance
    1.07
    empl
    1.02
     illustration
    1.01
    Activations Density 2.927%

    No Known Activations