© 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. 8-RES_POST_32K-OAI
    11. 5139
    Prev
    Next
    INDEX
    Explanations

    references to children and child-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    575
    +0.12
    0.5%
    157
    +0.09
    0.4%
    383
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.05
    281
    +0.09
    0.03
    325
    +0.09
    0.04
    Negative Logits
    PORT
    -0.64
    ATIVE
    -0.63
     manifold
    -0.62
    PROV
    -0.61
    ATION
    -0.60
    ATIONS
    -0.60
    ENCE
    -0.58
    Http
    -0.57
    ventory
    -0.57
    Accessory
    -0.56
    POSITIVE LOGITS
    ishly
    0.98
    sle
    0.90
     born
    0.88
    riages
    0.87
    children
    0.86
     ages
    0.85
    child
    0.84
    ults
    0.84
    bearing
    0.82
    chool
    0.81
    Activations Density 0.096%

    No Known Activations