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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11369
    Prev
    Next
    INDEX
    Explanations

    large numbers of people being involved in a gathering or event

    oai_token-act-pair · gpt-3.5-turbo

    mentions of large groups of people or crowd sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immortality
    -0.80
    terms
    -0.78
    ufact
    -0.74
    fusc
    -0.69
    Rating
    -0.68
     relativity
    -0.67
    opia
    -0.66
    ogenesis
    -0.65
     monopoly
    -0.65
    ocol
    -0.64
    POSITIVE LOGITS
     demonstrators
    1.23
     protesters
    1.23
     spectators
    1.13
     protestors
    1.13
     rallied
    1.04
     marched
    1.02
     onlook
    1.01
     volunteers
    1.00
     supporters
    0.98
     mourn
    0.95
    Activations Density 0.176%

    No Known Activations