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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 20040
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases that explain causation or contrast

    oai_token-act-pair · gpt-3.5-turbo

    clauses that serve as explanations or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +++
    -0.71
     Furious
    -0.63
    ossier
    -0.62
    bably
    -0.62
     nonetheless
    -0.61
    Mac
    -0.60
     Bucks
    -0.60
    sometimes
    -0.60
     Happ
    -0.60
     Frenzy
    -0.60
    POSITIVE LOGITS
    lihood
    0.70
     sexes
    0.69
    qt
    0.66
    hetical
    0.66
    ance
    0.65
     Americ
    0.65
    hemat
    0.62
    rings
    0.62
    geries
    0.62
    oping
    0.61
    Activations Density 0.138%

    No Known Activations