© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20411
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking a stand or position on an issue

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements about the state of being or existence

    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
    eor
    -0.65
    luaj
    -0.64
     floats
    -0.62
    stop
    -0.61
     throats
    -0.60
    sche
    -0.59
     captcha
    -0.59
    itches
    -0.58
    wrote
    -0.58
     curls
    -0.58
    POSITIVE LOGITS
     definitely
    1.09
     probably
    1.07
     certainly
    1.07
     usually
    1.05
     preferable
    1.04
     akin
    1.04
    rael
    1.00
     undoubtedly
    0.99
     tant
    0.99
     gonna
    0.98
    Activations Density 0.255%

    No Known Activations