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. 20905
    Prev
    Next
    INDEX
    Explanations

    references to the city of Windsor

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Windsor

    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
    onom
    -0.73
     PAY
    -0.72
    GAN
    -0.72
    Squ
    -0.72
     Pant
    -0.68
     Lean
    -0.67
     compens
    -0.67
     bip
    -0.67
    etary
    -0.66
    opal
    -0.66
    POSITIVE LOGITS
     Windsor
    3.13
    inding
    1.59
     Sidney
    1.15
     Sussex
    1.10
    IND
    1.06
    itious
    1.02
     Yiannopoulos
    1.02
     Cinderella
    1.01
     Dup
    1.01
     Dover
    1.01
    Activations Density 0.048%

    No Known Activations