© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20727
    Prev
    Next
    INDEX
    Explanations

    words related to various professions or occupations

    oai_token-act-pair · gpt-3.5-turbo

    references to various professions and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meier
    -0.73
     Oo
    -0.71
     Sudan
    -0.66
    arding
    -0.63
    borgh
    -0.63
    noon
    -0.63
     MAD
    -0.63
     Panzer
    -0.62
    Phones
    -0.60
     straw
    -0.59
    POSITIVE LOGITS
    ession
    0.91
    smanship
    0.89
     Profession
    0.83
    ically
    0.82
     association
    0.79
     profession
    0.78
    Builder
    0.78
    rities
    0.75
     associations
    0.75
    istry
    0.74
    Activations Density 0.023%

    No Known Activations