© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29948
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue from various literary and biblical sources

    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
    314
    +0.16
    0.7%
    420
    +0.13
    0.6%
    450
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.16
    0.10
    160
    +0.13
    0.10
    107
    +0.12
    0.09
    Negative Logits
     GPS
    -0.83
     adrenaline
    -0.79
     tabloid
    -0.76
     goof
    -0.75
     COP
    -0.75
     SAF
    -0.75
     kids
    -0.74
     locals
    -0.74
     tabl
    -0.74
     viral
    -0.74
    POSITIVE LOGITS
    Thus
    1.33
    tis
    1.24
    upon
    1.21
    shall
    1.19
    whose
    1.17
    Ye
    1.16
    Therefore
    1.15
    Whereas
    1.14
    Upon
    1.14
    Such
    1.12
    Activations Density 0.550%

    No Known Activations