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. 8525
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly focusing on the name "John", and words related to selling or buying

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms associated with commerce and transactions

    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
     Friendly
    -0.71
    Trigger
    -0.64
     Empress
    -0.63
     Typh
    -0.62
    astically
    -0.62
     Radar
    -0.62
     stringent
    -0.61
     silence
    -0.60
     Scene
    -0.60
     Engels
    -0.59
    POSITIVE LOGITS
    john
    3.15
    sold
    1.92
     john
    1.89
    ivan
    1.40
     redeem
    1.30
    yson
    1.25
    jon
    1.14
    wayne
    1.12
    ubuntu
    1.10
    ilton
    1.09
    Activations Density 0.049%

    No Known Activations