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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11364
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "bulls" as well as related words like "pit bulls" and "elephant seal bulls."

    oai_token-act-pair · gpt-3.5-turbo

    references to "bulls" and notable individuals associated with them

    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
     Squirrel
    -0.72
     Tide
    -0.72
     pirate
    -0.70
     turtle
    -0.67
    RAL
    -0.67
     monarch
    -0.67
     Colonial
    -0.66
     orphan
    -0.65
     Meadow
    -0.65
     Violet
    -0.64
    POSITIVE LOGITS
     Strauss
    1.93
     bulls
    1.88
    rugged
    1.14
    DNA
    1.12
    Rating
    1.05
    idis
    1.03
     vend
    1.00
    Stra
    0.96
     Dani
    0.96
     Rwanda
    0.93
    Activations Density 0.072%

    No Known Activations