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

    Neuronpedia

    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. 3-RES-JB
    11. 9566
    Prev
    Next
    INDEX
    Explanations

    phrases related to booking or making arrangements in advance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to making reservations, particularly in restaurant and service contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.72
    ogg
    -0.72
    src
    -0.72
    obs
    -0.72
    berman
    -0.69
    utenberg
    -0.68
    á½
    -0.68
    external
    -0.67
    oct
    -0.67
    sis
    -0.67
    POSITIVE LOGITS
     reservations
    1.31
     reservation
    1.30
     Reserv
    0.95
    ervation
    0.83
    erved
    0.77
    erv
    0.77
     rentals
    0.76
    erve
    0.76
     tickets
    0.75
    irmation
    0.75
    Activations Density 0.013%

    No Known Activations