© 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. 17189
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, most notably mountains

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, events, or timelines in narratives

    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
     Cosponsors
    -0.86
    awi
    -0.68
     cleaners
    -0.65
    theless
    -0.65
     locations
    -0.60
    omever
    -0.60
     likes
    -0.59
     strengths
    -0.59
    ierrez
    -0.58
     qualities
    -0.57
    POSITIVE LOGITS
    enium
    0.77
     millennium
    0.70
    iggurat
    0.69
    window
    0.67
     countdown
    0.65
    ilogy
    0.65
    \'
    0.64
     cycle
    0.64
     (~
    0.64
    yrus
    0.63
    Activations Density 0.475%

    No Known Activations