© 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. 1848
    Prev
    Next
    INDEX
    Explanations

    words related to bags, specifically purses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "purse" and significant associated concepts like "Fen" and "Europa."

    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
     Bend
    -0.80
    hatt
    -0.80
     Hamm
    -0.79
     Rosenberg
    -0.76
    aband
    -0.75
     Schwarzenegger
    -0.74
     Loving
    -0.72
    agascar
    -0.72
    >[
    -0.72
     Manson
    -0.72
    POSITIVE LOGITS
     purse
    1.90
     Fen
    1.75
     feather
    1.37
     penn
    1.34
     Europa
    1.32
     Edgar
    1.25
     fairy
    1.21
     curtain
    1.14
     Pens
    1.12
     Jackie
    1.04
    Activations Density 0.063%

    No Known Activations