© 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. 28153
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a process or methodology

    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
    678
    +0.15
    0.7%
    480
    +0.11
    0.5%
    619
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.15
    0.17
    43
    +0.11
    0.13
    546
    +0.11
    0.12
    Negative Logits
    ibles
    -0.68
     Redemption
    -0.65
    earned
    -0.61
    Lost
    -0.60
    ?????-
    -0.59
     Resistance
    -0.58
     Pigs
    -0.58
     Uri
    -0.58
    CTV
    -0.57
     whom
    -0.56
    POSITIVE LOGITS
     avoiding
    1.08
     minimizing
    1.04
     maximizing
    0.94
     concentrating
    0.92
     eliminating
    0.91
     ensuring
    0.86
     horizontally
    0.84
     preserving
    0.83
     using
    0.82
     relying
    0.82
    Activations Density 1.366%

    No Known Activations