© 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. 11-RES-JB
    11. 10284
    Prev
    Next
    INDEX
    Explanations

    politics and current events-related words or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to authority and events involving decision-making or actions

    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
    "]=>
    -0.74
     Cosponsors
    -0.71
    Recommend
    -0.68
    dayName
    -0.66
    .):
    -0.64
    astern
    -0.63
    omy
    -0.63
    imb
    -0.62
    ":[{"
    -0.61
     Obj
    -0.61
    POSITIVE LOGITS
     looming
    1.45
     nearing
    1.24
     dwindling
    1.19
     approaching
    1.13
     fading
    1.12
     dominating
    1.09
     coming
    1.08
     seeming
    1.06
     gone
    1.06
     disappearing
    1.05
    Activations Density 0.256%

    No Known Activations