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. 11-RES-JB
    6. 7415
    Prev
    Next
    INDEX
    Explanations

    the proper noun "Scarlett" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "Sc" followed by various letters in a context suggesting a geographic or institutional reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laure
    -0.67
     lapse
    -0.67
    terday
    -0.64
     thumbs
    -0.63
     wholesale
    -0.62
    etheless
    -0.61
     coupled
    -0.61
     Lights
    -0.61
     matching
    -0.58
     Prelude
    -0.57
    POSITIVE LOGITS
    ulpt
    1.42
    ratch
    1.40
    ripp
    1.29
    ooter
    1.22
    herer
    1.21
    enario
    1.20
    opes
    1.18
    enic
    1.14
    andal
    1.14
    apego
    1.14
    Activations Density 0.015%

    No Known Activations