Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8236
    Prev
    Next
    INDEX
    Explanations

    instances of reservations or appointments being made

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "booked" and its variations, indicating reservations or appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.84
    ple
    -0.79
    sburg
    -0.73
    berman
    -0.72
    ï¸ı
    -0.72
    Downloadha
    -0.69
    atism
    -0.68
    bite
    -0.67
    child
    -0.67
    vous
    -0.67
    POSITIVE LOGITS
    urations
    0.81
     booking
    0.79
     booked
    0.78
     flights
    0.76
    Kings
    0.74
     reservations
    0.72
     appointments
    0.69
     rentals
    0.69
    holder
    0.68
    holders
    0.68
    Activations Density 0.022%

    No Known Activations