© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reports

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation in the text

    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
     intending
    -0.78
     mechanically
    -0.74
    sequently
    -0.72
     immersion
    -0.69
     phenomen
    -0.67
     exha
    -0.67
     mosqu
    -0.66
     myster
    -0.65
     thous
    -0.64
     dimensional
    -0.64
    POSITIVE LOGITS
    <|endoftext|>
    1.24
     Subscribe
    1.14
     POLITICO
    1.10
    PHOTOS
    0.99
     READ
    0.98
     WATCH
    0.98
     SEE
    0.97
     Scroll
    0.94
     CLICK
    0.93
     Photo
    0.92
    Activations Density 0.299%

    No Known Activations