© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    phrases related to money and funding activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial allocations and fundraising

    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
    ierre
    -0.78
    ettings
    -0.66
     schematic
    -0.64
    ITNESS
    -0.60
     photographed
    -0.60
    spect
    -0.59
    picture
    -0.59
    tons
    -0.59
    ModLoader
    -0.59
     selfie
    -0.58
    POSITIVE LOGITS
     fund
    1.22
     coffers
    1.19
     reimburse
    1.19
     reinvest
    1.13
     funds
    1.12
     redistributed
    1.11
     Funds
    1.11
     repaid
    1.10
     reimb
    1.08
     subsid
    1.08
    Activations Density 0.318%

    No Known Activations