Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-RES-JB
    6. 10973
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising activities

    oai_token-act-pair · gpt-3.5-turbo

    references to crowdfunding platforms and fundraising efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯ãĥ³
    -0.82
    ãĥĥãĥī
    -0.80
    ãĥ¼ãĥ
    -0.75
    kov
    -0.75
    faces
    -0.70
     faults
    -0.68
    ussen
    -0.66
    isky
    -0.66
    opol
    -0.65
     wrinkles
    -0.64
    POSITIVE LOGITS
     donation
    1.27
     donated
    1.25
     fundraising
    1.25
     donating
    1.23
     donations
    1.23
     fundra
    1.20
     donate
    1.19
     fundraiser
    1.16
     Donation
    1.13
     donors
    1.01
    Activations Density 0.275%

    No Known Activations