Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 24238
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that stand out as important or significant

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "highlighted"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opic
    -0.75
    proxy
    -0.72
    wives
    -0.71
    cible
    -0.71
    cas
    -0.66
    wife
    -0.65
    appro
    -0.64
    eties
    -0.63
    atell
    -0.63
    hold
    -0.63
    POSITIVE LOGITS
     highlighted
    0.85
    ocument
    0.84
    umenthal
    0.78
     highlighting
    0.76
    TextColor
    0.74
    OWS
    0.72
     prominently
    0.70
     warnings
    0.69
     contrasting
    0.69
     highlights
    0.67
    Activations Density 0.016%

    No Known Activations