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. 23731
    Prev
    Next
    INDEX
    Explanations

    words related to a specific entity, potentially a person named "Hickenlooper"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Hickenlooper."

    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
     nom
    -0.65
     Mandatory
    -0.64
    atography
    -0.60
    rw
    -0.59
    oret
    -0.59
     mileage
    -0.58
     doc
    -0.58
     breakthrough
    -0.58
    doc
    -0.57
    NPR
    -0.56
    POSITIVE LOGITS
    icken
    1.25
    backer
    1.03
    ergy
    0.98
    bats
    0.91
    cies
    0.87
    anguage
    0.83
    fold
    0.83
    hs
    0.82
    ilage
    0.81
    aughs
    0.79
    Activations Density 0.007%

    No Known Activations