© 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. 8-RES-JB
    11. 3300
    Prev
    Next
    INDEX
    Explanations

    names of actors or entertainment industry professionals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gans
    -0.85
    istical
    -0.82
    oric
    -0.72
    reatment
    -0.72
    orship
    -0.72
    enser
    -0.71
    essing
    -0.70
    rison
    -0.70
    idate
    -0.69
    ivities
    -0.69
    POSITIVE LOGITS
     Alfred
    0.75
     Cowboy
    0.73
     Jasper
    0.73
     Esper
    0.73
     Beautiful
    0.73
     Brig
    0.72
     Exodus
    0.72
     Bald
    0.72
     Martha
    0.71
     Jeremiah
    0.71
    Activations Density 0.153%

    No Known Activations