© 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. 6-RES-JB
    11. 9178
    Prev
    Next
    INDEX
    Explanations

    mentions of crew members and their activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific group of people referred to as "crew."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fem
    -0.79
     Tend
    -0.68
    pend
    -0.66
    ãĥ¤
    -0.65
    incial
    -0.64
    itia
    -0.63
    mobi
    -0.63
    stract
    -0.62
     Bout
    -0.62
    ibaba
    -0.62
    POSITIVE LOGITS
    members
    1.40
    member
    1.21
    mates
    1.08
    wreck
    0.96
    smanship
    0.88
     member
    0.88
     members
    0.87
    shed
    0.85
     mates
    0.84
     aboard
    0.84
    Activations Density 0.021%

    No Known Activations