© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29782
    Prev
    Next
    INDEX
    Explanations

    URLs or references to online content

    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
    107
    +0.10
    0.4%
    313
    +0.09
    0.4%
    430
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.10
    0.04
    107
    +0.09
    0.04
    430
    +0.09
    0.03
    Negative Logits
     accur
    -0.69
     Sins
    -0.68
     NEC
    -0.65
     Mellon
    -0.65
     notices
    -0.65
     dise
    -0.64
     biod
    -0.64
     outnumbered
    -0.63
     Scotia
    -0.63
    theless
    -0.63
    POSITIVE LOGITS
    com
    1.49
    twitter
    1.14
    blogspot
    1.11
    wordpress
    1.01
    org
    0.99
    tumblr
    0.97
    COM
    0.94
    be
    0.94
    eu
    0.92
    push
    0.86
    Activations Density 0.047%

    No Known Activations