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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4220
    Prev
    Next
    INDEX
    Explanations

    mentions of money and fundraising activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettings
    -0.72
    ierre
    -0.72
    Í
    -0.66
    ModLoader
    -0.64
    Temperature
    -0.63
    Introduced
    -0.63
     histories
    -0.62
    uder
    -0.62
     archetype
    -0.60
     epoch
    -0.59
    POSITIVE LOGITS
     redistributed
    1.18
     fund
    1.14
     repaid
    1.14
     reinvest
    1.13
     allocated
    1.11
     donated
    1.10
     deposited
    1.09
     funds
    1.06
     accrued
    1.04
     payable
    1.02
    Activations Density 0.414%

    No Known Activations