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. 7-RES-JB
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    the indefinite article "a"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "It's a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Versions
    -0.82
    Edit
    -0.82
    DOM
    -0.79
    units
    -0.76
    Orig
    -0.75
    agues
    -0.74
    ographs
    -0.70
    items
    -0.68
    notes
    -0.68
    TPS
    -0.67
    POSITIVE LOGITS
     fascinating
    1.09
     lot
    1.04
     huge
    1.01
     simple
    1.01
     reminder
    1.00
     coincidence
    0.97
     bit
    0.96
     daunting
    0.93
     nice
    0.93
     continuation
    0.92
    Activations Density 0.196%

    No Known Activations