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. 11-RES-JB
    6. 3216
    Prev
    Next
    INDEX
    Explanations

    occurrences of events being hosted or gatherings taking place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "host" and its variations in various contexts

    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
    uca
    -0.66
     ILCS
    -0.64
    issued
    -0.62
     sidx
    -0.61
    illard
    -0.61
    Publisher
    -0.60
    taboola
    -0.59
    intent
    -0.59
    Availability
    -0.58
    ר
    -0.57
    POSITIVE LOGITS
     seminars
    1.20
     gatherings
    1.11
     meetings
    1.10
     exhibitions
    1.10
     workshops
    1.06
     consultations
    1.05
     conventions
    1.04
     conferences
    1.04
     fundra
    1.04
     events
    1.03
    Activations Density 0.103%

    No Known Activations