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. 2-RES-JB
    6. 164
    Prev
    Next
    INDEX
    Explanations

    the syllable "Sch"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "Sch" followed by a numerical value, potentially related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    the name "Sch" followed by various suffixes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censored
    -0.79
     monarch
    -0.73
    LECT
    -0.73
    DragonMagazine
    -0.73
     futures
    -0.69
    Downloadha
    -0.68
     constrained
    -0.68
     visitation
    -0.67
    EStream
    -0.65
     permitting
    -0.64
    POSITIVE LOGITS
    izoph
    1.28
    acht
    1.12
    utz
    1.05
    izophren
    1.01
    afer
    1.00
    umann
    1.00
    aeper
    0.96
    acher
    0.95
    ram
    0.94
    ulz
    0.93
    Activations Density 0.008%

    No Known Activations