© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7637
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "yers" with different contexts, potentially related to various individuals or professions

    oai_token-act-pair · gpt-3.5-turbo

    the word "lawyers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imper
    -0.70
     Bas
    -0.66
     Orb
    -0.66
     Disc
    -0.64
     Ï
    -0.62
     responsible
    -0.62
     Shroud
    -0.61
     tab
    -0.61
     fr
    -0.61
     pac
    -0.60
    POSITIVE LOGITS
    yers
    4.60
    yer
    1.70
    yles
    1.14
    orney
    1.12
    yre
    1.07
    orneys
    1.04
    suits
    0.98
     lawy
    0.97
    instein
    0.96
    ansas
    0.96
    Activations Density 0.007%

    No Known Activations