© 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. 24116
    Prev
    Next
    INDEX
    Explanations

    words related to professionals or experts

    oai_token-act-pair · gpt-3.5-turbo

    references to people associated with certain roles or positions, particularly in contexts involving service or care

    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
     Galile
    -0.89
     Palm
    -0.67
     Toledo
    -0.67
     Bahrain
    -0.65
     [|
    -0.65
     Cambridge
    -0.65
     Akron
    -0.63
     Lima
    -0.63
     GIF
    -0.62
     Flash
    -0.61
    POSITIVE LOGITS
    rs
    1.56
    mith
    1.25
    ession
    1.09
    agnar
    1.04
    essions
    1.01
    urance
    1.00
    ubs
    0.97
    essed
    0.96
    terday
    0.96
    ucker
    0.94
    Activations Density 0.006%

    No Known Activations