© 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. 31233
    Prev
    Next
    INDEX
    Explanations

    terms related to moral or existential themes

    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
    576
    +0.12
    0.5%
    151
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.00
    701
    +0.11
    0.01
    182
    +0.11
    0.01
    Negative Logits
    cember
    -0.75
    ivated
    -0.74
    urat
    -0.73
    >)
    -0.71
    inventoryQuantity
    -0.67
    ilater
    -0.67
    endiary
    -0.66
    ////////////////////////////////
    -0.64
    xtap
    -0.64
    STD
    -0.64
    POSITIVE LOGITS
     Skydragon
    0.65
     Mutant
    0.63
     Winged
    0.63
     reven
    0.62
     Simulator
    0.61
     Queen
    0.61
     Duchess
    0.59
    cake
    0.59
     Fist
    0.58
     Divinity
    0.56
    Activations Density 0.028%

    No Known Activations