© 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. 10312
    Prev
    Next
    INDEX
    Explanations

    specific mentions of appearances, especially on TV programs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" and related phrases indicating appearances or events

    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
    MpServer
    -0.63
    imilation
    -0.61
    ãĤ£
    -0.61
    gdala
    -0.60
    Types
    -0.60
    pdf
    -0.59
    enance
    -0.59
    abwe
    -0.59
    merce
    -0.59
     fing
    -0.58
    POSITIVE LOGITS
    screen
    1.44
     stage
    1.28
    stage
    1.13
     screen
    1.08
     behalf
    1.06
    etime
    1.06
     television
    0.98
     Broadway
    0.94
     Oprah
    0.90
     Showtime
    0.88
    Activations Density 0.129%

    No Known Activations