© 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. 0-RES-JB
    11. 16384
    Prev
    Next
    INDEX
    Explanations

    phrases related to buying or obtaining tickets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilic
    -0.70
    ogen
    -0.68
    natural
    -0.66
    hov
    -0.66
     âĨij
    -0.65
    stant
    -0.64
    gha
    -0.63
    gru
    -0.63
    ishi
    -0.61
    Begin
    -0.61
    POSITIVE LOGITS
     tickets
    3.87
     Tickets
    2.95
     ticket
    2.83
    Tickets
    2.62
     Ticket
    2.39
    ticket
    2.11
     seats
    1.71
    ickets
    1.60
     fares
    1.50
     invitations
    1.47
    Activations Density 0.012%

    No Known Activations