© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8160
    Prev
    Next
    INDEX
    Explanations

    references to left-handedness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to handedness, specifically in the context of sports or activities

    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
    atis
    -1.00
    PsyNetMessage
    -0.93
    hya
    -0.83
    ĸļ
    -0.82
    riott
    -0.81
    ynt
    -0.80
    xus
    -0.80
    actionDate
    -0.80
    usky
    -0.79
    antz
    -0.79
    POSITIVE LOGITS
     batters
    0.90
    erers
    0.89
    ness
    0.85
     hitter
    0.84
     stroke
    0.83
    erer
    0.80
     nodd
    0.78
    llor
    0.76
     Nadu
    0.75
     arrow
    0.74
    Activations Density 0.047%

    No Known Activations