© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5080
    Prev
    Next
    INDEX
    Explanations

    initials of notable people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    capital letters or proper nouns, likely indicating notable names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adobe
    -0.74
    theless
    -0.72
    éĹĺ
    -0.70
    ãĥ´
    -0.62
    DragonMagazine
    -0.59
    »Ĵ
    -0.56
    SAM
    -0.56
    ItemTracker
    -0.55
    wake
    -0.55
    gpu
    -0.53
    POSITIVE LOGITS
    .,
    1.78
    .?
    1.68
    .:
    1.60
    .;
    1.56
    .,"
    1.50
    ./
    1.49
    .'
    1.29
    .),
    1.29
    .—
    1.29
    .-
    1.29
    Activations Density 0.062%

    No Known Activations