© 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. 31645
    Prev
    Next
    INDEX
    Explanations

    phrases indicating extreme conditions or unusual comparisons

    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
    705
    +0.11
    0.5%
    376
    +0.10
    0.5%
    757
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.11
    0.06
    102
    +0.10
    0.08
    647
    +0.09
    0.05
    Negative Logits
    soDeliveryDate
    -0.74
    rities
    -0.71
     advis
    -0.65
     Kills
    -0.65
    iences
    -0.64
    utical
    -0.63
    asking
    -0.63
     Dreams
    -0.62
     Caption
    -0.62
    phies
    -0.62
    POSITIVE LOGITS
     visc
    0.89
    Ë
    0.82
     variable
    0.82
     uniform
    0.79
     uniformly
    0.78
     compact
    0.77
     concentrated
    0.77
     slender
    0.77
    atten
    0.76
     abundant
    0.76
    Activations Density 0.900%

    No Known Activations