© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 32201
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their counts

    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
    237
    +0.13
    0.6%
    376
    +0.11
    0.5%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.13
    0.05
    373
    +0.11
    -0.02
    316
    +0.10
    0.04
    Negative Logits
    enne
    -0.82
    nir
    -0.74
    iments
    -0.68
    een
    -0.68
    enance
    -0.66
    nant
    -0.64
    Iowa
    -0.63
    lam
    -0.63
     Niet
    -0.61
    ream
    -0.61
    POSITIVE LOGITS
    gin
    0.82
    GP
    0.75
    ger
    0.69
    ggles
    0.69
    grain
    0.67
    ggy
    0.66
    Ķ
    0.65
    ĺħ
    0.65
     conduc
    0.63
    otation
    0.63
    Activations Density 0.410%

    No Known Activations