© 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. 8-RES_POST_32K-OAI
    11. 6080
    Prev
    Next
    INDEX
    Explanations

    the definite article "the"

    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
    314
    +0.09
    0.4%
    469
    +0.09
    0.4%
    756
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.09
    0.11
    393
    +0.09
    0.07
    608
    +0.09
    0.08
    Negative Logits
     Became
    -0.72
     Accessed
    -0.63
    fab
    -0.61
    olin
    -0.60
    oris
    -0.59
    iband
    -0.57
    fecture
    -0.57
    fw
    -0.57
    meg
    -0.56
     indefinitely
    -0.56
    POSITIVE LOGITS
     others
    0.98
     counterparts
    0.96
     rest
    0.89
     originals
    0.87
     norm
    0.85
     alternatives
    0.84
     ones
    0.84
     predecessors
    0.82
     competitors
    0.82
     previous
    0.81
    Activations Density 0.554%

    No Known Activations