© 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. 18236
    Prev
    Next
    INDEX
    Explanations

    specific job titles or roles related to technology and the arts

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to creative and technical professions

    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
     rivals
    -0.82
     republic
    -0.79
     king
    -0.79
     bisc
    -0.77
     overhaul
    -0.76
     empire
    -0.76
     rehab
    -0.76
     kings
    -0.76
     ÂŃ
    -0.75
     blitz
    -0.75
    POSITIVE LOGITS
     Designer
    1.78
     Developer
    1.75
     Artist
    1.71
     Engineer
    1.69
     Administrator
    1.65
     Advisor
    1.64
     Analyst
    1.63
     Operator
    1.63
     Producer
    1.62
     Investigator
    1.62
    Activations Density 0.062%

    No Known Activations