© 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. 10-RES-JB
    11. 6634
    Prev
    Next
    INDEX
    Explanations

    references to events, meetings, and actions being held or planned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hold" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibel
    -0.72
    ghan
    -0.71
    eson
    -0.66
    product
    -0.65
    ÃŁ
    -0.65
    âĺ
    -0.64
    annabin
    -0.62
    Rated
    -0.62
     burd
    -0.61
    !/
    -0.61
    POSITIVE LOGITS
     hearings
    1.19
     meetings
    1.19
     consultations
    1.09
     rallies
    1.07
     conferences
    1.05
    ezvous
    1.05
     gatherings
    1.04
     seminars
    1.03
     workshops
    0.98
     auctions
    0.92
    Activations Density 0.072%

    No Known Activations