© 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. 8-RES-JB
    11. 4233
    Prev
    Next
    INDEX
    Explanations

    formal titles such as "sir" and "Senator"

    oai_token-act-pair · gpt-3.5-turbo

    terms of address or titles used in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prev
    -0.70
     culminating
    -0.64
    essional
    -0.59
    alli
    -0.59
     tether
    -0.59
    icago
    -0.58
    CONCLUS
    -0.58
     occas
    -0.58
    Loading
    -0.57
    accessible
    -0.56
    POSITIVE LOGITS
     sir
    0.95
    ratulations
    0.91
    !
    0.86
    !'
    0.81
    !"
    0.79
    !,
    0.77
     dear
    0.76
     please
    0.76
     gentlemen
    0.75
     thou
    0.75
    Activations Density 0.165%

    No Known Activations