© 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. 8-RES_POST_32K-OAI
    11. 5672
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "Par" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    60
    +0.15
    0.7%
    314
    +0.13
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.15
    0.03
    515
    +0.13
    0.02
    124
    +0.10
    0.02
    Negative Logits
    éĹĺ
    -0.72
     divest
    -0.70
     dwar
    -0.63
     decay
    -0.62
     darling
    -0.60
     flask
    -0.60
     compromise
    -0.58
     Ceres
    -0.58
    !/
    -0.58
     completion
    -0.57
    POSITIVE LOGITS
    lez
    1.16
    agon
    1.09
    anoia
    1.07
    rish
    1.05
    agraph
    1.04
    amed
    0.98
    onto
    0.96
    rill
    0.94
    inton
    0.93
    vati
    0.93
    Activations Density 0.043%

    No Known Activations