© 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. 8-RES-JB
    11. 20357
    Prev
    Next
    INDEX
    Explanations

    phrases or terms with the structure "think of" followed by a particular concept or idea

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that suggest a pattern of thought or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.67
    pite
    -0.65
     contended
    -0.63
     declared
    -0.61
     cess
    -0.60
    ante
    -0.60
     proclaimed
    -0.60
    Mp
    -0.60
     contained
    -0.60
     asserts
    -0.60
    POSITIVE LOGITS
    agine
    0.66
     ways
    0.66
     Hein
    0.63
     quitting
    0.62
    agus
    0.61
     how
    0.61
    hetically
    0.60
    din
    0.60
     them
    0.59
    èĪ
    0.59
    Activations Density 0.056%

    No Known Activations