© 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. 2330
    Prev
    Next
    INDEX
    Explanations

    words related to genius or exceptional intelligence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to generation and familial connections

    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
    SPONSORED
    -0.86
    assment
    -0.78
    notation
    -0.77
     Crab
    -0.77
     Creep
    -0.75
    Bear
    -0.74
     Drill
    -0.70
    bucks
    -0.70
    isse
    -0.69
    cre
    -0.68
    POSITIVE LOGITS
     gen
    1.99
     reun
    1.74
     Doctors
    1.64
     dyn
    1.45
     ty
    1.40
     Amer
    1.18
     reunited
    1.15
     famine
    1.10
     Dyn
    1.10
     polio
    1.04
    Activations Density 0.045%

    No Known Activations