© 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. 30269
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have" and its variations in different 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
    523
    +0.11
    0.5%
    629
    +0.11
    0.5%
    208
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.11
    0.12
    668
    +0.11
    0.11
    547
    +0.10
    0.08
    Negative Logits
     realise
    -0.81
     realised
    -0.77
     learnt
    -0.73
     reproduce
    -0.72
     forgot
    -0.71
    «ĺ
    -0.71
     invented
    -0.68
     hereby
    -0.65
     congr
    -0.65
    ovember
    -0.63
    POSITIVE LOGITS
     spar
    0.93
    Critics
    0.88
     clashed
    0.86
     brist
    0.83
     Critics
    0.80
     staunch
    0.80
     rocky
    0.79
     criticized
    0.77
     outspoken
    0.77
     skepticism
    0.76
    Activations Density 0.570%

    No Known Activations