© 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. 21213
    Prev
    Next
    INDEX
    Explanations

    capitalized terms related to software or data formatting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "IM"

    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
    yards
    -0.88
    rooms
    -0.78
     greens
    -0.72
    Accessory
    -0.69
    yard
    -0.67
     scratch
    -0.67
     Guinness
    -0.66
    naires
    -0.65
     Parables
    -0.65
     Borough
    -0.64
    POSITIVE LOGITS
    PLIC
    1.19
    PLE
    1.00
    achine
    0.98
    orph
    0.97
    IM
    0.97
    pson
    0.95
    MY
    0.93
    MED
    0.92
    unity
    0.90
    perial
    0.89
    Activations Density 0.006%

    No Known Activations