© 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. 2-RES-JB
    11. 17086
    Prev
    Next
    INDEX
    Explanations

    mentions of places or locations referred to as "hotspots"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hotspots in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.75
    xit
    -0.70
    ogy
    -0.68
    PRESS
    -0.66
    yss
    -0.66
    nered
    -0.66
     Suff
    -0.63
     Sep
    -0.63
     Sweeney
    -0.62
    lly
    -0.61
    POSITIVE LOGITS
    pots
    1.49
    pot
    1.33
     hots
    1.31
     Hots
    1.16
    hots
    0.97
    combe
    0.95
    atile
    0.93
    pur
    0.87
    visor
    0.83
    bucks
    0.81
    Activations Density 0.009%

    No Known Activations