© 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. 9-RES-JB
    11. 11678
    Prev
    Next
    INDEX
    Explanations

    sentences articulating strong opinions or emphasizing specific points

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and its repeated use in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.76
     sacrific
    -0.69
     seiz
    -0.66
     Also
    -0.61
    essor
    -0.61
    anwhile
    -0.61
    ynasty
    -0.60
     destro
    -0.59
    abulary
    -0.59
     necks
    -0.59
    POSITIVE LOGITS
    ifiable
    1.30
    ifications
    1.05
     plain
    0.98
    if
    0.86
     kidding
    0.85
     icing
    0.84
    ified
    0.83
    IFIED
    0.83
     desserts
    0.82
    IFIC
    0.75
    Activations Density 0.092%

    No Known Activations