© 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. 24223
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Francis"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Franc" and its variations

    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
     Occupations
    -0.68
     Pharma
    -0.67
    BOX
    -0.66
     Tycoon
    -0.66
    TOP
    -0.65
     Hyde
    -0.65
     Bounce
    -0.65
     partName
    -0.64
     Hussain
    -0.64
     Anchorage
    -0.63
    POSITIVE LOGITS
    ophone
    1.14
     franc
    1.03
     Franc
    1.00
    isco
    0.96
    Franc
    0.95
    clair
    0.93
    ibel
    0.90
     citiz
    0.84
    aud
    0.84
    ophile
    0.84
    Activations Density 0.005%

    No Known Activations