© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 3690
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Com"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comedy related to "Com" or "Comedy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mara
    -0.72
     Kubrick
    -0.71
     halfway
    -0.69
     Icelandic
    -0.67
     harbor
    -0.63
     Labyrinth
    -0.63
     Refuge
    -0.62
     Aval
    -0.62
     gratification
    -0.59
     Krug
    -0.59
    POSITIVE LOGITS
    fortable
    1.32
    puters
    1.28
    pletion
    1.28
    pleting
    1.27
    mented
    1.20
    plex
    1.18
    puting
    1.16
    ptroller
    1.15
    plement
    1.15
    ittee
    1.11
    Activations Density 0.030%

    No Known Activations