© 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. 30596
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web development and programming

    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
    564
    +0.10
    0.4%
    502
    +0.09
    0.4%
    445
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.10
    0.03
    326
    +0.09
    0.04
    314
    +0.08
    -0.01
    Negative Logits
     Collider
    -0.81
     behavi
    -0.79
    itive
    -0.74
     Behavior
    -0.71
     Cave
    -0.68
     perspect
    -0.66
    ized
    -0.66
    istically
    -0.65
     Unlock
    -0.62
    VERTISEMENT
    -0.62
    POSITIVE LOGITS
    special
    1.02
    info
    0.94
    ls
    0.93
    lc
    0.86
    bin
    0.86
    ns
    0.84
    ll
    0.82
    tan
    0.82
    mid
    0.81
    ln
    0.81
    Activations Density 0.242%

    No Known Activations