© 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. 10-RES-JB
    11. 18867
    Prev
    Next
    INDEX
    Explanations

    words related to extreme positivity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "uber" and terms related to high quality or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     challeng
    -0.68
     Lans
    -0.66
     hig
    -0.64
     crane
    -0.63
    YS
    -0.63
    mania
    -0.61
    berries
    -0.60
    NetMessage
    -0.59
    ccoli
    -0.59
     haz
    -0.57
    POSITIVE LOGITS
    ations
    2.70
    ation
    2.62
    ators
    2.34
    ating
    2.24
    ated
    2.16
    ator
    2.15
    atory
    2.14
    ative
    2.07
    ATIONS
    2.00
    ates
    1.97
    Activations Density 0.381%

    No Known Activations