© 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. 10-RES-JB
    11. 20599
    Prev
    Next
    INDEX
    Explanations

    terms related to restriction, prohibition or lack of something, specifically focusing on 'free' words

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "free" in various contexts, especially related to lifestyle and dietary choices

    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
    actionDate
    -0.82
    foreseen
    -0.81
    skilled
    -0.80
    skill
    -0.76
    SEA
    -0.73
    rawdownloadcloneembedreportprint
    -0.72
    confirmed
    -0.67
    IGHTS
    -0.66
    luence
    -0.65
    inus
    -0.65
    POSITIVE LOGITS
     zones
    0.96
    lihood
    0.94
    zing
    0.91
     zone
    0.90
    glers
    0.89
    ness
    0.87
    zers
    0.84
    ze
    0.82
    NESS
    0.81
    bies
    0.78
    Activations Density 0.123%

    No Known Activations