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

    Neuronpedia

    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. 4317
    Prev
    Next
    INDEX
    Explanations

    specific pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo
    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
    emale
    -0.69
    luster
    -0.66
     topp
    -0.66
    Interstitial
    -0.64
     smashing
    -0.64
     exting
    -0.62
     moderation
    -0.62
     scra
    -0.62
     slashing
    -0.61
     theme
    -0.61
    POSITIVE LOGITS
     know
    1.36
    know
    1.32
     KNOW
    1.32
    Know
    1.28
     knows
    1.22
    knowledge
    1.20
     knew
    1.19
     Know
    1.14
     knowing
    1.09
    Knowing
    1.03
    Activations Density 0.367%

    No Known Activations