© 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. 11-RES-JB
    11. 20992
    Prev
    Next
    INDEX
    Explanations

    adjectives describing tasks that are demanding, challenging, or complex

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenging tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.90
     References
    -0.74
    TextColor
    -0.71
    values
    -0.69
     Ratings
    -0.69
    Spons
    -0.67
    Cola
    -0.66
    drops
    -0.66
    letters
    -0.66
    edia
    -0.66
    POSITIVE LOGITS
     task
    1.98
     endeavor
    1.63
     ardu
    1.54
     undertaking
    1.52
     process
    1.50
     endeavour
    1.50
     tasks
    1.46
     feat
    1.45
     job
    1.38
     chore
    1.31
    Activations Density 0.525%

    No Known Activations