© 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. 31829
    Prev
    Next
    INDEX
    Explanations

    expressions of trust and assurances

    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
    350
    +0.12
    0.5%
    747
    +0.11
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.12
    0.05
    449
    +0.11
    0.04
    274
    +0.11
    0.04
    Negative Logits
    SPONSORED
    -0.67
     undermin
    -0.65
     facult
    -0.60
    endas
    -0.57
     alternatively
    -0.56
    ynthesis
    -0.55
     Possible
    -0.54
     Explain
    -0.54
     Novel
    -0.52
    ories
    -0.51
    POSITIVE LOGITS
     anytime
    0.86
    zers
    0.74
     none
    0.73
     it
    0.67
     nobody
    0.66
    zen
    0.66
     there
    0.63
     Trey
    0.63
     whenever
    0.62
    there
    0.61
    Activations Density 0.750%

    No Known Activations