© 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. 20046
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's physical presence or participation in an event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "appearance."

    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
    imb
    -0.81
    rals
    -0.78
    bard
    -0.74
    bern
    -0.73
    pex
    -0.73
    rup
    -0.69
    aiman
    -0.69
    erness
    -0.67
    ythm
    -0.67
     consortium
    -0.66
    POSITIVE LOGITS
     appearances
    0.89
    lihood
    0.87
     appearance
    0.84
     Appearance
    0.74
    ants
    0.67
    antly
    0.67
    æ³
    0.64
     announcements
    0.64
     Discrimination
    0.63
     Incarn
    0.62
    Activations Density 0.046%

    No Known Activations