© 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. 30926
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers, particularly in reference to votes or ratings

    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
    316
    +0.12
    0.5%
    308
    +0.11
    0.5%
    412
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.12
    0.01
    18
    +0.11
    0.01
    405
    +0.11
    0.01
    Negative Logits
     wounding
    -0.67
    ONSORED
    -0.64
     encl
    -0.62
    ]=
    -0.61
     interrupt
    -0.60
    =$
    -0.60
     Pavilion
    -0.59
     paraly
    -0.58
     distraction
    -0.58
     :=
    -0.58
    POSITIVE LOGITS
    onne
    0.85
    roman
    0.74
    uca
    0.71
    eatures
    0.70
    Mine
    0.70
    roid
    0.69
    lez
    0.69
    Runtime
    0.68
    )</
    0.67
    630
    0.66
    Activations Density 0.026%

    No Known Activations