© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and chances

    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
    373
    +0.13
    0.6%
    684
    +0.12
    0.5%
    456
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.13
    0.04
    247
    +0.12
    0.03
    4
    +0.09
    0.04
    Negative Logits
     Winning
    -0.61
    irie
    -0.60
    apor
    -0.58
    hemat
    -0.58
    erno
    -0.56
     Dying
    -0.56
    agate
    -0.56
    essel
    -0.55
     Zip
    -0.55
    hod
    -0.54
    POSITIVE LOGITS
    iaz
    0.77
    Reviewer
    0.73
     to
    0.69
    ãĥīãĥ©ãĤ´ãĥ³
    0.62
    erity
    0.61
     chance
    0.60
    assetsadobe
    0.59
     choose
    0.59
    idates
    0.59
    isf
    0.58
    Activations Density 0.193%

    No Known Activations