© 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. 8-RES_POST_32K-OAI
    11. 7556
    Prev
    Next
    INDEX
    Explanations

    first-person narratives expressing personal experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    204
    +0.12
    0.6%
    532
    +0.11
    0.5%
    400
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.06
    762
    +0.11
    0.06
    397
    +0.11
    0.05
    Negative Logits
    hiba
    -0.64
     opt
    -0.62
     nevertheless
    -0.60
    æĪ¦
    -0.59
    isky
    -0.58
    ETF
    -0.57
     ETF
    -0.57
     nonetheless
    -0.56
     juxtap
    -0.54
    ixels
    -0.54
    POSITIVE LOGITS
     usual
    0.99
    usual
    0.98
     customary
    0.88
     normally
    0.78
    should
    0.76
     predecessors
    0.76
    planned
    0.75
     intended
    0.70
    fits
    0.68
    expected
    0.67
    Activations Density 0.655%

    No Known Activations