© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27703
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Amy" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    575
    +0.12
    0.5%
    167
    +0.11
    0.5%
    351
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    374
    +0.11
    0.00
    232
    +0.10
    0.02
    Negative Logits
    iffe
    -0.74
    initialized
    -0.73
    veland
    -0.70
    lights
    -0.69
    IFIED
    -0.65
    UGE
    -0.64
    maker
    -0.62
    soDeliveryDate
    -0.58
    animous
    -0.58
     Bucs
    -0.56
    POSITIVE LOGITS
    gdala
    1.73
    gd
    1.13
     Schumer
    1.03
     GOODMAN
    1.01
    puter
    0.98
    cus
    0.94
     Wine
    0.90
    dor
    0.87
    borgh
    0.85
    matically
    0.83
    Activations Density 0.093%

    No Known Activations