© 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. 8-RES_POST_32K-OAI
    11. 7105
    Prev
    Next
    INDEX
    Explanations

    instances of the suffix "ile" 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
    36
    +0.12
    0.6%
    756
    +0.12
    0.6%
    110
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    110
    +0.12
    0.02
    514
    +0.12
    0.01
    Negative Logits
    ĸļ
    -0.90
    ington
    -0.78
    ãĥĦ
    -0.77
    ingham
    -0.76
    ipeg
    -0.76
    sylvania
    -0.75
    icum
    -0.74
    itivity
    -0.74
    iversal
    -0.73
    ĵĺ
    -0.70
    POSITIVE LOGITS
    mma
    1.12
    tto
    1.02
    vich
    0.82
    ttes
    0.81
    tt
    0.77
    psy
    0.76
    aments
    0.75
    llan
    0.73
    tta
    0.72
    tsky
    0.71
    Activations Density 0.104%

    No Known Activations