© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15116
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or plans that a person was supposed to attend or participate in

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events and attendance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     hardness
    -0.81
     trillions
    -0.79
     Patent
    -0.77
     deflation
    -0.74
    ©¶æ¥µ
    -0.73
    llular
    -0.73
     brute
    -0.73
     Penet
    -0.72
     Weak
    -0.71
     immutable
    -0.71
    POSITIVE LOGITS
    Tickets
    1.56
     itiner
    1.40
     attendance
    1.37
     booked
    1.33
     scheduling
    1.30
     calendars
    1.26
     Tickets
    1.25
     postponed
    1.25
     tickets
    1.23
     scheduled
    1.22
    Activations Density 1.211%

    No Known Activations