© 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. 8-RES_POST_32K-OAI
    11. 4192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in various contexts

    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
    49
    +0.14
    0.6%
    766
    +0.12
    0.5%
    715
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.14
    0.06
    608
    +0.12
    0.05
    665
    +0.08
    0.05
    Negative Logits
     Sector
    -0.65
     fulfillment
    -0.61
     Gears
    -0.61
    æ³
    -0.60
    hazard
    -0.59
     fits
    -0.58
     signifies
    -0.58
     interests
    -0.57
    âĿ
    -0.57
     handles
    -0.57
    POSITIVE LOGITS
     simply
    0.84
    inka
    0.76
     pretend
    0.71
    heny
    0.71
     convince
    0.70
    yrinth
    0.70
     imagine
    0.70
    owell
    0.70
    udding
    0.70
     starve
    0.70
    Activations Density 0.161%

    No Known Activations