© 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. 31447
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "go" and its forms in various 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
    200
    +0.10
    0.5%
    473
    +0.10
    0.5%
    759
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.10
    0.06
    377
    +0.10
    0.06
    437
    +0.10
    0.04
    Negative Logits
     Helic
    -0.81
     Fiesta
    -0.68
     Collider
    -0.68
     Pizza
    -0.66
     Controlled
    -0.66
     RG
    -0.66
     mega
    -0.64
     Massive
    -0.64
     bunny
    -0.63
     pandemonium
    -0.62
    POSITIVE LOGITS
     forth
    1.20
     abroad
    1.13
     thence
    1.05
     hither
    0.97
     ashore
    0.94
     onward
    0.93
     away
    0.90
     ast
    0.88
     awa
    0.87
     boldly
    0.86
    Activations Density 0.154%

    No Known Activations