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. 0-RES-JB
    6. 5774
    Prev
    Next
    INDEX
    Explanations

    names of political figures, particularly focusing on the surname ''Spicer''

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vale
    -0.71
     dystop
    -0.71
    Vol
    -0.71
     Dogs
    -0.70
     chapter
    -0.70
    gd
    -0.69
    AU
    -0.69
     Venus
    -0.68
     mineral
    -0.68
     Instrument
    -0.68
    POSITIVE LOGITS
     Spicer
    2.69
     Priebus
    2.63
     RNC
    2.30
    patrick
    1.41
     Nunes
    1.25
     Hannity
    1.14
    ince
    1.06
     Fiesta
    1.05
     Rove
    1.05
     FEC
    1.03
    Activations Density 0.035%

    No Known Activations