© 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. 9-RES-JB
    11. 15633
    Prev
    Next
    INDEX
    Explanations

    words related to general concepts or broad descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broad" and its variations

    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
     Tycoon
    -0.74
    ILLE
    -0.71
    illard
    -0.65
     Million
    -0.64
    rious
    -0.64
    ICAN
    -0.64
     âī¡
    -0.62
    ilon
    -0.61
     Keeper
    -0.61
    INO
    -0.61
    POSITIVE LOGITS
    sheet
    1.54
    sheets
    1.32
    ening
    1.27
     strokes
    1.14
    side
    1.12
    ened
    1.09
     spectrum
    1.09
    sword
    1.08
    leaf
    1.02
     swath
    0.98
    Activations Density 0.031%

    No Known Activations