© 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. 9-RES-JB
    11. 6045
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences starting with "Have you" or "Do you" and ending with a verb or question

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases that engage the listener or reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruciating
    -0.79
    umber
    -0.75
    Lago
    -0.72
    apo
    -0.68
    umbers
    -0.65
    alde
    -0.63
    accompan
    -0.62
    ges
    -0.61
    "},
    -0.61
    inelli
    -0.61
    POSITIVE LOGITS
     guys
    1.14
     ever
    1.09
     wanna
    0.90
    ever
    0.89
     agree
    0.89
     know
    0.87
    ?'
    0.85
     prefer
    0.84
     kidding
    0.84
     WATCHED
    0.84
    Activations Density 0.044%

    No Known Activations