© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 1311
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising and financial support

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the purpose of funding or financial support

    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
    iquette
    -0.82
    unciation
    -0.78
    spection
    -0.74
     disobedience
    -0.71
    ception
    -0.69
     Warning
    -0.68
     Parameters
    -0.68
    calling
    -0.67
    rend
    -0.64
     Caller
    -0.63
    POSITIVE LOGITS
     fund
    1.46
     compensate
    1.40
     renov
    1.37
     repay
    1.36
     reimburse
    1.36
     pay
    1.28
     subsid
    1.27
     buy
    1.23
     purchase
    1.22
     finance
    1.21
    Activations Density 0.137%

    No Known Activations