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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7239
    Prev
    Next
    INDEX
    Explanations

    terms of respect and address such as "sir" or specific names like "john"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly names and titles of respect

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

    No Comments

    Negative Logits
     Clinic
    -0.74
     healed
    -0.70
     Piercing
    -0.66
     Dying
    -0.66
     Surgery
    -0.66
     Lens
    -0.66
     Camer
    -0.65
    PDATE
    -0.64
     Leban
    -0.64
     Remem
    -0.64
    POSITIVE LOGITS
    otaur
    1.01
    athan
    1.01
    sb
    1.00
    gers
    0.99
    atory
    0.89
    son
    0.87
    tyard
    0.83
    gling
    0.83
    izen
    0.83
    ster
    0.83
    Activations Density 0.033%

    No Known Activations