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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15768
    Prev
    Next
    INDEX
    Explanations

    the word "Is"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IOR
    -0.78
    theless
    -0.69
    ĸļ
    -0.62
     lapse
    -0.61
     XD
    -0.61
    ãģĮ
    -0.58
     excise
    -0.57
     phrase
    -0.57
     digs
    -0.57
     Lann
    -0.56
    POSITIVE LOGITS
    olated
    1.59
    olation
    1.59
    olate
    1.52
    abella
    1.39
    rael
    1.33
    sei
    1.29
    peria
    1.24
    abel
    1.21
    htar
    1.16
    hma
    1.11
    Activations Density 0.057%

    No Known Activations