© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3343
    Prev
    Next
    INDEX
    Explanations

    the name "Frances" followed by another specific word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Frances."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocrine
    -0.85
    eering
    -0.74
     Helsinki
    -0.70
     racially
    -0.64
    ARK
    -0.62
     Honolulu
    -0.61
    eer
    -0.61
     Kuwait
    -0.61
    igators
    -0.60
    eers
    -0.60
    POSITIVE LOGITS
    terness
    1.21
     Frances
    1.15
    olini
    0.98
    coni
    0.88
    chini
    0.87
    owship
    0.87
    deen
    0.81
    cus
    0.80
    atell
    0.80
    cakes
    0.80
    Activations Density 0.007%

    No Known Activations