© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3269
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting up and organizing events or entities, like fundraising pages and working groups

    oai_token-act-pair · gpt-3.5-turbo

    references to funding and organizational support initiatives

    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
    ibles
    -0.75
     alike
    -0.73
    llah
    -0.67
    hops
    -0.66
    natureconservancy
    -0.65
    mith
    -0.64
    IDs
    -0.64
     Parenthood
    -0.61
    ittal
    -0.61
    ctors
    -0.61
    POSITIVE LOGITS
     behalf
    0.93
     Mondays
    0.67
     titled
    0.67
    ebin
    0.66
    lua
    0.66
     thanking
    0.63
    itled
    0.62
     identifying
    0.62
     estimating
    0.61
     inviting
    0.61
    Activations Density 0.555%

    No Known Activations