© 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. 30772
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or accumulation

    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
    147
    +0.13
    0.6%
    205
    +0.09
    0.4%
    667
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.08
    608
    +0.09
    0.07
    205
    +0.09
    0.03
    Negative Logits
    actionDate
    -0.74
    irection
    -0.73
    cffffcc
    -0.69
    avior
    -0.69
    CHAT
    -0.68
    NetMessage
    -0.68
    okemon
    -0.66
    interstitial
    -0.65
    soType
    -0.63
    pmwiki
    -0.62
    POSITIVE LOGITS
     repertoire
    1.21
     pile
    1.12
     list
    1.12
     already
    1.12
     mix
    1.10
     arsenal
    1.04
     existing
    1.04
     equation
    1.03
     coffers
    1.02
     tally
    0.98
    Activations Density 1.186%

    No Known Activations