© 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. 1-RES-JB
    6. 376
    Prev
    Next
    INDEX
    Explanations

    mentions of the professional cyclist Mark Cavendish

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cav"

    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
     rough
    -0.67
    tered
    -0.66
     silent
    -0.66
     comparative
    -0.65
    think
    -0.65
    tery
    -0.64
    binding
    -0.64
     redistributed
    -0.63
    tering
    -0.63
    utenant
    -0.63
    POSITIVE LOGITS
    endish
    1.30
     Cav
    1.22
    iar
    1.03
    inelli
    1.03
    illo
    0.95
    imir
    0.95
    olini
    0.93
    arella
    0.92
     Emin
    0.89
    ity
    0.88
    Activations Density 0.009%

    No Known Activations