© 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. 10-RES_POST_32K-OAI
    11. 30542
    Prev
    Next
    INDEX
    Explanations

    references to names or naming conventions

    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
    114
    +0.10
    0.5%
    603
    +0.10
    0.4%
    390
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.10
    0.03
    603
    +0.10
    0.03
    609
    +0.09
    0.03
    Negative Logits
    istar
    -0.75
    yrinth
    -0.71
    romy
    -0.69
     hurd
    -0.65
    icult
    -0.65
    senal
    -0.64
     gif
    -0.62
     Noon
    -0.62
    yrus
    -0.61
    oulos
    -0.60
    POSITIVE LOGITS
    plates
    1.50
    plate
    1.46
    paces
    1.40
    paced
    1.17
    brand
    0.91
    names
    0.89
     recognition
    0.87
    cloth
    0.84
    akes
    0.83
    calling
    0.81
    Activations Density 0.303%

    No Known Activations