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. 9524
    Prev
    Next
    INDEX
    Explanations

    phrases related to making donations or financial support

    oai_token-act-pair · gpt-3.5-turbo

    references to donations and support for independent projects or initiatives

    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
     inconsist
    -0.68
     interrogated
    -0.67
     detainees
    -0.67
     occupant
    -0.65
     msec
    -0.63
     occupants
    -0.63
     grapp
    -0.63
     interrogation
    -0.63
     handcuffed
    -0.63
     purported
    -0.62
    POSITIVE LOGITS
     donation
    1.64
     Donation
    1.60
     donations
    1.59
     Patreon
    1.57
     donate
    1.51
     donating
    1.40
     PayPal
    1.31
     pledge
    1.22
     Pledge
    1.16
     Contributions
    1.11
    Activations Density 0.266%

    No Known Activations