Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 19709
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative processes and activities

    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
    ilon
    -0.74
    thritis
    -0.73
     Royale
    -0.73
    ãģ¦
    -0.70
    PLIED
    -0.70
    lighting
    -0.67
     Mub
    -0.67
    schild
    -0.66
    ologists
    -0.65
    esm
    -0.65
    POSITIVE LOGITS
     redist
    0.90
     branch
    0.88
    atures
    0.85
     mand
    0.85
     adjourn
    0.85
     enact
    0.84
     drafting
    0.82
     enacted
    0.81
     session
    0.80
    woman
    0.80
    Activations Density 0.037%

    No Known Activations