© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1024
    Prev
    Next
    INDEX
    Explanations

    strings of text including specific letter combinations 'TI', 'ti', 'stad', 'sill', 'Strike', 'IFT', 'GE', and 'arette'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands, companies, or titles

    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
    wagen
    -1.00
    esville
    -0.81
     Pwr
    -0.80
    horse
    -0.74
    alter
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    coming
    -0.67
     gorilla
    -0.65
    ãĥ©ãĥ³
    -0.65
     Crimson
    -0.65
    POSITIVE LOGITS
     TI
    1.28
    TI
    1.26
    PS
    0.92
    PT
    0.89
    ented
    0.87
     Staples
    0.86
    OTAL
    0.86
    EMP
    0.78
    ------------------------------------------------
    0.78
    pered
    0.78
    Activations Density 0.013%

    No Known Activations