© 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. 11-RES-JB
    11. 14922
    Prev
    Next
    INDEX
    Explanations

    information about ticketing, events, and scheduling

    oai_token-act-pair · gpt-3.5-turbo

    phrases and information related to ticket purchases and event details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nsic
    -0.76
    seless
    -0.71
    icient
    -0.68
    Ò
    -0.65
     sentient
    -0.65
     spurious
    -0.64
    ´
    -0.64
    aturated
    -0.64
    anks
    -0.63
    odied
    -0.62
    POSITIVE LOGITS
     schedule
    1.43
     schedules
    1.38
     itiner
    1.34
    Tickets
    1.30
     Tickets
    1.29
     dates
    1.27
     Dates
    1.26
     tickets
    1.24
     timet
    1.19
     Schedule
    1.18
    Activations Density 0.284%

    No Known Activations