© 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. 8-RES-JB
    11. 22389
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Rolling Stone"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the publication "Rolling Stone."

    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
    neau
    -0.94
    lessly
    -0.85
    uchin
    -0.84
    earing
    -0.84
    seeing
    -0.83
    xual
    -0.82
    sense
    -0.81
    flies
    -0.80
    ittal
    -0.79
    SHIP
    -0.79
    POSITIVE LOGITS
     Stones
    0.98
     Stone
    0.90
     Rolling
    0.81
     Tide
    0.77
     Meadows
    0.66
    Stone
    0.65
     Papers
    0.65
     Tavern
    0.65
     Fest
    0.64
     Tribune
    0.62
    Activations Density 0.049%

    No Known Activations