© 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. 27272
    Prev
    Next
    INDEX
    Explanations

    specific structural elements related to publication or article formatting

    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
    +0.20
    1.0%
    533
    +0.09
    0.4%
    358
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.20
    -0.01
    111
    +0.09
    0.01
    666
    +0.08
    0.01
    Negative Logits
    edi
    -0.66
     Spoiler
    -0.65
    backer
    -0.61
     Hector
    -0.61
     Tina
    -0.60
    abilia
    -0.59
    eatures
    -0.59
     Converted
    -0.58
     Glas
    -0.58
    ictionary
    -0.56
    POSITIVE LOGITS
     killings
    0.62
     arrests
    0.61
    ivities
    0.59
    rings
    0.59
     stakes
    0.59
    agh
    0.58
     raids
    0.58
    comings
    0.58
    aks
    0.58
     holes
    0.57
    Activations Density 0.034%

    No Known Activations