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. 2-RES-JB
    6. 8705
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific public figures, such as "Limbaugh" and "Eminem"

    oai_token-act-pair · gpt-3.5-turbo

    prominent individuals and their associations in the context of media and controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ive
    -0.86
    yne
    -0.85
    het
    -0.85
    eers
    -0.84
    ively
    -0.81
    ivas
    -0.80
    iva
    -0.78
    ives
    -0.77
    76561
    -0.77
    ivities
    -0.75
    POSITIVE LOGITS
    baugh
    0.93
     Limbaugh
    0.90
     Harbaugh
    0.82
    ensional
    0.80
     McMahon
    0.70
    itual
    0.66
    ingo
    0.66
    XM
    0.64
     Pistons
    0.64
    ONSORED
    0.62
    Activations Density 0.015%

    No Known Activations