© 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 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. 9-RES-JB
    11. 2227
    Prev
    Next
    INDEX
    Explanations

    time-related information such as dates, times, and locations in event announcements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blackmail
    -0.81
     unintended
    -0.78
     botched
    -0.77
     trusts
    -0.77
     griev
    -0.74
     shrunk
    -0.73
     exasper
    -0.73
     shrew
    -0.72
     cheated
    -0.72
     spared
    -0.71
    POSITIVE LOGITS
    Tickets
    1.33
     Tickets
    1.29
     EVENT
    1.20
    Saturday
    1.19
     Admission
    1.14
     Doors
    1.12
     kickoff
    1.11
     Participants
    1.10
     Attend
    1.08
     Event
    1.06
    Activations Density 0.514%

    No Known Activations