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. 1-RES-JB
    6. 12599
    Prev
    Next
    INDEX
    Explanations

    words related to archaeology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to archeology and archetypes

    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
    abad
    -0.75
    backer
    -0.68
     Fully
    -0.66
     FISA
    -0.66
     Whip
    -0.65
    Guard
    -0.64
     Grind
    -0.64
     Electronic
    -0.62
    Assembly
    -0.62
    Freedom
    -0.60
    POSITIVE LOGITS
     arche
    1.23
    types
    1.02
     Arche
    1.01
    typ
    0.97
    ological
    0.91
    eteen
    0.88
    chwitz
    0.84
    umat
    0.83
    omorph
    0.83
    ologists
    0.82
    Activations Density 0.004%

    No Known Activations