© 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. 30802
    Prev
    Next
    INDEX
    Explanations

    details related to conversations and personal relationships

    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
    69
    +0.12
    0.6%
    32
    +0.12
    0.6%
    662
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.12
    0.01
    69
    +0.12
    0.07
    498
    +0.11
    0.09
    Negative Logits
     Mul
    -0.85
     Tec
    -0.85
     Chiefs
    -0.85
     Nec
    -0.83
    Cruz
    -0.83
    raid
    -0.82
     Kaw
    -0.82
     Niet
    -0.82
     bur
    -0.81
    \\\\\\\\\\\\\\\\
    -0.81
    POSITIVE LOGITS
     Gl
    2.11
     GL
    2.02
     gl
    1.99
    Gl
    1.98
    gl
    1.95
    GL
    1.86
     OpenGL
    1.45
    igl
    1.16
     gluten
    1.15
     Gladiator
    1.12
    Activations Density 7.577%

    No Known Activations