© 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 EvalsExportsAPI 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. 16040
    Prev
    Next
    INDEX
    Explanations

    references to presenting oneself or something to a broader audience or community, or words related to public interaction

    oai_token-act-pair · gpt-3.5-turbo

    references to the community and public awareness

    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
    illac
    -0.72
     preceded
    -0.71
     wherein
    -0.69
     according
    -0.68
    icut
    -0.68
     whereby
    -0.67
    gars
    -0.65
     namely
    -0.64
    cum
    -0.63
     together
    -0.62
    POSITIVE LOGITS
     populace
    1.22
     masses
    1.17
     audience
    1.15
     electorate
    1.07
     world
    1.05
     viewer
    1.05
     entire
    1.03
     rest
    0.99
     reader
    0.98
     viewers
    0.97
    Activations Density 0.310%

    No Known Activations