© 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. 1-RES-JB
    11. 18670
    Prev
    Next
    INDEX
    Explanations

    words related to the word "biscuit"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "isc" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.70
     Despair
    -0.68
     Siberian
    -0.65
     Debbie
    -0.64
     Stard
    -0.63
    STER
    -0.63
     Tibetan
    -0.63
     Squirrel
    -0.62
     fetch
    -0.62
     marrow
    -0.61
    POSITIVE LOGITS
    isc
    1.21
    onduct
    1.12
    ount
    1.10
    uity
    0.97
    retion
    0.96
    ault
    0.90
    rypted
    0.88
    urnal
    0.88
    ussed
    0.87
    ussion
    0.86
    Activations Density 0.011%

    No Known Activations