© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4778
    Prev
    Next
    INDEX
    Explanations

    references to groups of people or communities

    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
    314
    +0.17
    0.8%
    218
    +0.14
    0.6%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.17
    0.03
    241
    +0.14
    0.02
    232
    +0.12
    0.03
    Negative Logits
     Malfoy
    -0.71
    enegger
    -0.67
     laz
    -0.63
     Prelude
    -0.62
     Cain
    -0.62
     Palo
    -0.61
     Brock
    -0.58
     rake
    -0.57
     Diablo
    -0.56
     Bil
    -0.56
    POSITIVE LOGITS
    swer
    0.76
    cia
    0.74
     Eater
    0.73
    itton
    0.71
     magazine
    0.71
    uka
    0.70
     Magazine
    0.70
    ascript
    0.69
    oran
    0.69
    omore
    0.68
    Activations Density 0.186%

    No Known Activations