© 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. 27907
    Prev
    Next
    INDEX
    Explanations

    topics related to aging and life extension strategies

    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
    516
    +0.13
    0.6%
    69
    +0.12
    0.6%
    579
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.14
    83
    +0.12
    0.03
    137
    +0.11
    -0.00
    Negative Logits
     Ramsey
    -0.83
     sheep
    -0.83
    ÃŃa
    -0.82
     Rouse
    -0.81
    ÃŃ
    -0.79
    á¹
    -0.76
    lot
    -0.69
     Towns
    -0.69
     shepherd
    -0.69
    å
    -0.68
    POSITIVE LOGITS
    Ext
    2.04
     extension
    2.01
     Extension
    1.97
     extensions
    1.96
     Extensions
    1.91
    ext
    1.91
     Extend
    1.79
     Ext
    1.74
     Extended
    1.72
     extend
    1.60
    Activations Density 3.111%

    No Known Activations