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. 3-RES-JB
    6. 14125
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to specific names, perhaps locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "iw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     succeeding
    -0.74
     penetrating
    -0.71
     fracturing
    -0.71
    âĸ¬
    -0.67
     tamp
    -0.67
    greSQL
    -0.64
    âĸ¬âĸ¬
    -0.63
     elev
    -0.61
     mort
    -0.61
     surgeons
    -0.60
    POSITIVE LOGITS
    atts
    1.22
    iw
    1.17
    ield
    1.10
    ombo
    1.08
    esley
    1.07
    orthy
    1.02
    agy
    1.00
    atcher
    1.00
    itsu
    1.00
    ugi
    0.99
    Activations Density 0.006%

    No Known Activations