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. 0-RES-JB
    6. 19587
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising or asking for financial support

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of raising or increasing something, particularly in a financial or awareness context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ijn
    -0.70
    ilda
    -0.68
    Us
    -0.65
    hent
    -0.65
    Pict
    -0.63
    abase
    -0.62
    orno
    -0.62
    faces
    -0.62
    oman
    -0.61
    nation
    -0.61
    POSITIVE LOGITS
     raise
    3.68
     raises
    2.38
     Raise
    2.34
    raise
    2.19
     raising
    2.12
     raised
    2.02
    raised
    1.59
     increase
    1.29
    raising
    1.28
     hike
    1.24
    Activations Density 0.011%

    No Known Activations