© 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 EvalsExportsAPI 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. 30295
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in varying contexts

    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
    615
    +0.12
    0.5%
    522
    +0.09
    0.4%
    412
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.08
    608
    +0.09
    0.07
    393
    +0.09
    0.06
    Negative Logits
    tones
    -0.89
    yles
    -0.69
     intersections
    -0.67
    ulas
    -0.66
     rigs
    -0.66
     recommendations
    -0.66
     suites
    -0.66
    mares
    -0.65
    ulations
    -0.65
    ieties
    -0.65
    POSITIVE LOGITS
     bearer
    1.21
     beneficiary
    1.19
     aggress
    1.02
     guy
    1.02
     wiser
    1.02
     leader
    1.01
     underdog
    1.00
     smartest
    1.00
     recipient
    0.98
     protector
    0.97
    Activations Density 0.304%

    No Known Activations