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. 3490
    Prev
    Next
    INDEX
    Explanations

    the name "Galloway" with the context of being booed and negative events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of booing or negative reactions associated with specific individuals

    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
     Cooking
    -0.74
     Fortress
    -0.74
     Sprint
    -0.70
    Med
    -0.68
     Purg
    -0.68
     CPC
    -0.67
    Intel
    -0.67
     Newsweek
    -0.67
     CTR
    -0.67
     Spr
    -0.66
    POSITIVE LOGITS
     boo
    2.93
    oway
    2.34
     tem
    1.09
     woo
    1.07
    eson
    1.06
    Bey
    0.99
     Boo
    0.96
    helle
    0.88
    oley
    0.88
     DOM
    0.83
    Activations Density 0.029%

    No Known Activations