© 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. 3-RES-JB
    11. 7170
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names ending with "berg."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Berg" or similar spellings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.75
    IVES
    -0.65
     NOTICE
    -0.65
     millenn
    -0.62
    Latest
    -0.61
    mble
    -0.61
     runaway
    -0.60
    FUL
    -0.60
     respective
    -0.59
    versely
    -0.59
    POSITIVE LOGITS
    stein
    1.17
    hetti
    1.14
    enegger
    1.11
    berg
    1.07
    enstein
    1.02
    ersen
    1.01
    roth
    0.96
    ingen
    0.95
    heim
    0.94
    rade
    0.93
    Activations Density 0.014%

    No Known Activations