© 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. 8-RES_POST_32K-OAI
    11. 4673
    Prev
    Next
    INDEX
    Explanations

    references to studies and data related to genetics and intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    745
    +0.10
    0.4%
    349
    +0.09
    0.4%
    619
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.17
    575
    +0.09
    0.13
    698
    +0.09
    0.10
    Negative Logits
     hugs
    -0.76
    cott
    -0.67
     Shank
    -0.62
    å§
    -0.61
    Stretch
    -0.61
     Awakening
    -0.60
    ajor
    -0.60
    ario
    -0.58
    elected
    -0.57
    udeb
    -0.56
    POSITIVE LOGITS
     closely
    1.04
     carefully
    0.97
     objectively
    0.96
     favorably
    0.91
     trends
    0.88
     thoroughly
    0.85
     extensively
    0.82
     differently
    0.80
     suspic
    0.80
     aloud
    0.77
    Activations Density 2.252%

    No Known Activations