© 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. 6985
    Prev
    Next
    INDEX
    Explanations

    mentions of smoking

    oai_token-act-pair · gpt-3.5-turbo

    words related to smoking and its effects

    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
    heit
    -0.63
    rants
    -0.62
    Letter
    -0.60
     Lama
    -0.60
    DragonMagazine
    -0.60
     Tud
    -0.60
     Vanguard
    -0.60
     Highlander
    -0.59
     Cerberus
    -0.59
     quo
    -0.58
    POSITIVE LOGITS
    ooth
    1.38
    iley
    1.34
    oky
    1.32
    ugg
    1.30
    oked
    1.28
    oke
    1.27
    okers
    1.26
    oking
    1.25
    okes
    1.25
    oker
    1.23
    Activations Density 0.010%

    No Known Activations