Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10683
    Prev
    Next
    INDEX
    Explanations

    adverbs related to speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    instances of rapid change or movement

    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
    iar
    -0.77
    yon
    -0.65
     Disclosure
    -0.63
    orn
    -0.63
     Courtesy
    -0.62
     BaseType
    -0.61
    arations
    -0.60
    duty
    -0.60
    Extra
    -0.59
     exception
    -0.59
    POSITIVE LOGITS
     rapidly
    3.35
     quickly
    2.17
     steadily
    2.11
     swiftly
    2.09
     slowly
    2.03
     gradually
    1.91
     rapid
    1.59
     progressively
    1.56
     furiously
    1.53
     dramatically
    1.51
    Activations Density 0.010%

    No Known Activations