© 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. 0-RES-JB
    11. 1219
    Prev
    Next
    INDEX
    Explanations

    words related to large gatherings of people

    oai_token-act-pair · gpt-3.5-turbo

    references to crowds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Term
    -0.76
     TAMADRA
    -0.69
    âĺħ
    -0.67
    :\
    -0.67
     Terms
    -0.64
    termination
    -0.63
    arella
    -0.62
    Documents
    -0.62
    Relations
    -0.62
    én
    -0.61
    POSITIVE LOGITS
     crowd
    3.88
     crowds
    2.78
     Crowd
    2.39
    rowd
    2.22
     audience
    1.79
     mob
    1.45
     crowded
    1.26
     spectators
    1.20
     audiences
    1.20
     herd
    1.17
    Activations Density 0.027%

    No Known Activations