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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4853
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" used in various contexts

    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
    662
    +0.11
    0.5%
    726
    +0.10
    0.5%
    132
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.11
    0.02
    377
    +0.10
    0.02
    258
    +0.10
    0.02
    Negative Logits
    eus
    -0.75
    emort
    -0.69
    iants
    -0.60
     parap
    -0.60
    \\\\\\\\
    -0.60
    %]
    -0.60
    ernand
    -0.59
    atche
    -0.58
    iquette
    -0.58
    atl
    -0.57
    POSITIVE LOGITS
     ago
    1.11
     Ago
    0.91
     longer
    0.87
    cium
    0.69
     overdue
    0.68
    OOK
    0.67
    ä
    0.61
    ndra
    0.60
    night
    0.60
     hiatus
    0.60
    Activations Density 0.029%

    No Known Activations