© 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. 26842
    Prev
    Next
    INDEX
    Explanations

    negative prefixes indicating a lack or absence of something

    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
    569
    +0.12
    0.5%
    503
    +0.09
    0.4%
    748
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.12
    0.02
    232
    +0.09
    0.03
    616
    +0.09
    0.02
    Negative Logits
     culture
    -0.71
     umbrella
    -0.67
    undy
    -0.66
     freeze
    -0.64
     fulfillment
    -0.64
    anwhile
    -0.64
     painting
    -0.62
     simulations
    -0.62
     tone
    -0.61
     flowering
    -0.61
    POSITIVE LOGITS
    hibited
    1.03
    structed
    1.02
    erved
    0.97
    cipl
    0.96
    served
    0.93
    readable
    0.92
    PASS
    0.91
    jured
    0.90
    achable
    0.90
    notice
    0.89
    Activations Density 0.090%

    No Known Activations