© 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. 0-RES-JB
    11. 22182
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms and jargon

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with specialized or informal language, including jargon and slang

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctuary
    -0.72
    ener
    -0.71
    Poll
    -0.68
    Save
    -0.68
     Independent
    -0.64
     ATK
    -0.64
     independent
    -0.60
    Secret
    -0.59
    emaker
    -0.59
    Independent
    -0.59
    POSITIVE LOGITS
     terminology
    2.85
     jargon
    2.56
     slang
    2.12
     acron
    1.82
     vocabulary
    1.71
    peak
    1.68
     concepts
    1.65
    oqu
    1.64
    speak
    1.62
    lance
    1.53
    Activations Density 0.031%

    No Known Activations