© 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. 29139
    Prev
    Next
    INDEX
    Explanations

    programming-related elements and structures, particularly those pertaining to algorithms and data types

    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
    449
    +0.11
    0.5%
    516
    +0.11
    0.5%
    341
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.11
    0.03
    375
    +0.11
    0.04
    669
    +0.10
    0.07
    Negative Logits
    NRS
    -0.77
     PARK
    -0.75
     polic
    -0.72
    ¥µ
    -0.71
    fet
    -0.71
    etts
    -0.70
    TPP
    -0.69
    oby
    -0.69
    Ry
    -0.68
    »
    -0.68
    POSITIVE LOGITS
     Al
    2.51
    Al
    2.32
     al
    1.83
     AL
    1.80
     Alb
    1.51
     Alm
    1.38
     Alph
    1.33
    al
    1.32
     Ala
    1.28
    AL
    1.27
    Activations Density 3.908%

    No Known Activations