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. 0-RES-JB
    6. 3668
    Prev
    Next
    INDEX
    Explanations

    references to the city of Seattle

    oai_token-act-pair · gpt-3.5-turbo

    references to Seattle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GC
    -0.72
     Lib
    -0.72
     FD
    -0.65
     bases
    -0.65
     cop
    -0.62
     mod
    -0.62
     prescription
    -0.61
     Univers
    -0.60
     base
    -0.60
     supervised
    -0.59
    POSITIVE LOGITS
    attle
    4.37
    ATTLE
    1.51
    attled
    1.50
    iddle
    1.03
    ascal
    1.00
    abbage
    0.98
    addle
    0.97
    aukee
    0.97
    attery
    0.96
    oultry
    0.96
    Activations Density 0.024%

    No Known Activations