© 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. 20324
    Prev
    Next
    INDEX
    Explanations

    instances of the string "isch"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the substring "isch."

    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
     NCT
    -0.75
    20439
    -0.74
     Grateful
    -0.69
     Aval
    -0.67
    ndum
    -0.65
     Ground
    -0.65
    vernment
    -0.63
    DIT
    -0.60
     Hurricanes
    -0.60
     Crescent
    -0.60
    POSITIVE LOGITS
    isch
    1.49
    mann
    1.06
    itect
    0.97
    itzer
    0.94
    ovy
    0.93
    lich
    0.91
    stadt
    0.90
    heimer
    0.88
    inski
    0.86
    hoff
    0.85
    Activations Density 0.005%

    No Known Activations