© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Mehmet" and its variations 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
    120
    +0.09
    0.4%
    747
    +0.09
    0.4%
    300
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.03
    232
    +0.09
    0.03
    744
    +0.09
    0.03
    Negative Logits
    kefeller
    -0.88
    ĸļ
    -0.75
    otine
    -0.74
    ļéĨĴ
    -0.69
    ichick
    -0.68
     racket
    -0.68
    NetMessage
    -0.67
     Venture
    -0.67
    uador
    -0.66
    ":[{"
    -0.65
    POSITIVE LOGITS
    cott
    0.76
    lers
    0.76
    ollah
    0.75
    rets
    0.74
    aji
    0.72
    downs
    0.72
    stones
    0.71
    bats
    0.71
    oku
    0.70
    gom
    0.70
    Activations Density 0.117%

    No Known Activations