© 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. 27430
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and its various forms and conjugations

    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
    756
    +0.11
    0.5%
    360
    +0.11
    0.5%
    55
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.14
    102
    +0.11
    0.13
    7
    +0.11
    0.10
    Negative Logits
     punches
    -0.76
    illon
    -0.71
     warranties
    -0.70
    aughs
    -0.70
    thood
    -0.70
     fares
    -0.69
    erity
    -0.69
    20439
    -0.67
     Calls
    -0.67
    soever
    -0.66
    POSITIVE LOGITS
     inhabited
    1.44
     frequ
    1.44
     deserted
    1.34
     littered
    1.33
     populated
    1.33
     situated
    1.29
     located
    1.28
     inaccessible
    1.25
     occupied
    1.21
     guarded
    1.20
    Activations Density 0.963%

    No Known Activations