© 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. 7-RES-JB
    6. 21728
    Prev
    Next
    INDEX
    Explanations

    words related to arguments and explanations

    oai_token-act-pair · gpt-3.5-turbo

    arguments and discussions surrounding claims or premises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abytes
    -0.82
    usercontent
    -0.68
     bowel
    -0.67
    ibles
    -0.67
    ãĥīãĥ©
    -0.65
     stockpile
    -0.64
    robe
    -0.64
     renovations
    -0.63
    interrupted
    -0.63
    unte
    -0.62
    POSITIVE LOGITS
     empir
    0.90
     argument
    0.82
    argument
    0.81
     rhetorical
    0.80
     Chomsky
    0.79
     fallacy
    0.78
     causation
    0.77
     Aristotle
    0.77
     empirical
    0.77
     paradox
    0.76
    Activations Density 0.862%

    No Known Activations