© 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. 4-RES-JB
    11. 6915
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to expressing emotions or ideas

    oai_token-act-pair · gpt-3.5-turbo

    the term "expression" and its various contexts and interpretations

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

    No Comments

    Negative Logits
     Brewers
    -0.78
     Shades
    -0.78
     Bullets
    -0.77
    ether
    -0.71
    END
    -0.70
    Ń·
    -0.70
    ICK
    -0.67
     Claus
    -0.67
    sonian
    -0.66
     Down
    -0.65
    POSITIVE LOGITS
    terday
    0.97
     expression
    0.88
     expressions
    0.87
     guiActiveUn
    0.83
     Expression
    0.78
    express
    0.77
    ivity
    0.76
    ively
    0.75
    uses
    0.75
    pieces
    0.74
    Activations Density 0.015%

    No Known Activations