© 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. 0-RES-JB
    11. 19236
    Prev
    Next
    INDEX
    Explanations

    the surname "Raza."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals associated with the La Raza organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writer
    -0.74
     blame
    -0.74
     typ
    -0.67
     reign
    -0.66
     Pats
    -0.66
    Writer
    -0.63
     reins
    -0.63
     Thin
    -0.62
     lean
    -0.61
     Reign
    -0.60
    POSITIVE LOGITS
    aza
    4.71
    azaar
    1.37
    azo
    1.31
    az
    1.25
    abo
    1.18
    iza
    1.09
    azar
    1.08
    azi
    1.08
    ambo
    1.06
    alez
    1.01
    Activations Density 0.010%

    No Known Activations