© 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. 10-RES-JB
    11. 4222
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'bold' in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bold" used to describe significant actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTOS
    -0.70
     Cheong
    -0.70
     duly
    -0.67
    enfranch
    -0.61
     Surv
    -0.59
     patiently
    -0.58
    ruciating
    -0.58
     Bulletin
    -0.57
     Dise
    -0.57
     Warfare
    -0.57
    POSITIVE LOGITS
    faced
    1.35
    face
    1.21
    er
    1.17
    ness
    1.14
    est
    1.05
    mouth
    0.96
    card
    0.90
    ened
    0.84
    nesses
    0.81
    eyed
    0.81
    Activations Density 0.042%

    No Known Activations