© 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. 31979
    Prev
    Next
    INDEX
    Explanations

    numerical values and expressions in text

    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
    46
    +0.13
    0.6%
    694
    +0.11
    0.5%
    693
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.05
    289
    +0.11
    0.01
    96
    +0.09
    0.03
    Negative Logits
     �
    -0.90
     ''
    -0.74
    soDeliveryDate
    -0.74
     Mr
    -0.70
     dors
    -0.70
     quotation
    -0.68
     Dill
    -0.64
     paternity
    -0.62
     photograph
    -0.62
     Tup
    -0.61
    POSITIVE LOGITS
    +
    2.78
    +.
    2.23
    +,
    2.20
    +)
    2.07
    +(
    1.98
    ++
    1.77
    -+
    1.74
    +++
    1.67
    )+
    1.59
    +=
    1.52
    Activations Density 0.397%

    No Known Activations