© 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. 29051
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or potential

    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
    340
    +0.12
    0.6%
    139
    +0.11
    0.5%
    538
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.12
    551
    +0.11
    0.11
    49
    +0.11
    0.11
    Negative Logits
     compan
    -0.73
     Membership
    -0.66
     Volunte
    -0.65
     Suggest
    -0.65
    minist
    -0.65
    schild
    -0.64
     republican
    -0.64
     Governments
    -0.64
     pledging
    -0.63
     recommendation
    -0.62
    POSITIVE LOGITS
     score
    0.98
    score
    0.94
     drib
    0.92
     defensively
    0.90
     scoring
    0.89
     rebound
    0.89
     offensively
    0.87
     platoon
    0.86
    scoring
    0.85
     Jarrett
    0.84
    Activations Density 0.517%

    No Known Activations