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. 10-RES-JB
    6. 9744
    Prev
    Next
    INDEX
    Explanations

    punctuation marks related to dialogue

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "As you know."

    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
    resents
    -0.73
    raq
    -0.72
    Parameters
    -0.71
    Cause
    -0.70
    emaker
    -0.69
    oward
    -0.68
    ipel
    -0.66
    irms
    -0.66
    orge
    -0.65
    SourceFile
    -0.65
    POSITIVE LOGITS
     however
    1.14
     there
    1.05
     none
    1.02
     although
    1.00
     though
    1.00
     nobody
    0.97
     neither
    0.95
    there
    0.90
     despite
    0.86
     THERE
    0.84
    Activations Density 0.176%

    No Known Activations