© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5086
    Prev
    Next
    INDEX
    Explanations

    copyright symbols and related text

    oai_token-act-pair · gpt-3.5-turbo

    copyright symbols and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favor
    -0.67
    cknow
    -0.66
    atem
    -0.66
    itious
    -0.66
    uyomi
    -0.65
     assum
    -0.64
    rency
    -0.63
     retard
    -0.62
     favour
    -0.62
    ushi
    -0.61
    POSITIVE LOGITS
    Copyright
    1.03
     Copyright
    0.90
    wcsstore
    0.86
    ©
    0.84
    english
    0.82
    POL
    0.81
    2017
    0.79
    2018
    0.79
    1999
    0.78
    2015
    0.76
    Activations Density 0.011%

    No Known Activations