© 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. 0-RES-JB
    11. 1573
    Prev
    Next
    INDEX
    Explanations

    German words related to specific locations or people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or name

    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
     licence
    -0.84
     endeavour
    -0.70
     firmly
    -0.70
     succession
    -0.67
     tightly
    -0.67
     populated
    -0.65
     favour
    -0.65
     regulated
    -0.64
     contract
    -0.64
     Flor
    -0.63
    POSITIVE LOGITS
    atz
    4.84
    etz
    1.50
    atan
    1.27
    itz
    1.22
    tz
    1.11
    antz
    1.09
    chwitz
    1.08
    itsch
    1.06
    haar
    1.05
    witz
    1.03
    Activations Density 0.012%

    No Known Activations