© 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. 18973
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to starting or initiating an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of starting points or thresholds in various contexts

    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
    Downloadha
    -0.74
     Journalism
    -0.73
    ussia
    -0.70
    vich
    -0.64
    pict
    -0.63
     billed
    -0.60
    allowed
    -0.57
     SERV
    -0.56
    ussian
    -0.55
    services
    -0.55
    POSITIVE LOGITS
     point
    1.89
     end
    1.43
    point
    1.39
     conclusion
    1.32
     outset
    1.32
     bottom
    1.25
     points
    1.25
     beginning
    1.23
     Point
    1.22
     endpoint
    1.22
    Activations Density 0.419%

    No Known Activations