© 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. 8-RES-JB
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    phrases related to joining or being a part of a group or program

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "join" and its variations in different contexts

    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
    merce
    -0.71
    andi
    -0.67
    pex
    -0.66
    ibia
    -0.64
    prototype
    -0.64
    intendent
    -0.63
    robe
    -0.62
    bane
    -0.62
    icz
    -0.62
     tiss
    -0.61
    POSITIVE LOGITS
     forces
    1.00
     ranks
    0.86
     Forces
    0.78
    TAIN
    0.77
    fleet
    0.75
    OOL
    0.73
     Starfleet
    0.71
    itored
    0.71
     hands
    0.70
    ATURES
    0.69
    Activations Density 0.039%

    No Known Activations