© 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. 31806
    Prev
    Next
    INDEX
    Explanations

    comic book issue numbers

    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
    314
    +0.15
    0.7%
    260
    +0.10
    0.5%
    425
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.15
    0.02
    430
    +0.10
    0.02
    442
    +0.10
    0.03
    Negative Logits
     Lumpur
    -0.90
     behavi
    -0.71
     conflic
    -0.70
     upd
    -0.69
     Nanto
    -0.67
     ann
    -0.66
     lag
    -0.66
     moder
    -0.64
     xen
    -0.64
     neb
    -0.63
    POSITIVE LOGITS
    1
    1.42
    2
    1.20
    III
    1.19
    3
    1.14
    II
    1.13
    ½
    1.09
    VII
    1.03
    5
    1.02
    6
    1.01
    7
    1.01
    Activations Density 0.118%

    No Known Activations