© 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. 8-RES-JB
    11. 1255
    Prev
    Next
    INDEX
    Explanations

    mentions of funding and financial details

    oai_token-act-pair · gpt-3.5-turbo

    information related to financial investments and funding in projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acists
    -0.84
    ghazi
    -0.81
    wrong
    -0.77
    acist
    -0.77
     tyranny
    -0.74
     dreaded
    -0.74
     hated
    -0.73
     truth
    -0.72
     shameful
    -0.72
     racists
    -0.72
    POSITIVE LOGITS
     upgr
    1.09
     2021
    1.00
     rollout
    0.96
     2019
    0.95
     phased
    0.95
     suppliers
    0.95
     2020
    0.92
    ufact
    0.91
     refurb
    0.90
     operational
    0.90
    Activations Density 1.105%

    No Known Activations