© 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. 0-RES-JB
    6. 11383
    Prev
    Next
    INDEX
    Explanations

    terms related to professional occupations

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of professionals

    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
    agram
    -0.70
    vari
    -0.69
    lude
    -0.68
    ain
    -0.65
    jar
    -0.64
     Seat
    -0.64
    hed
    -0.63
    hide
    -0.63
    version
    -0.62
    reg
    -0.61
    POSITIVE LOGITS
     professionals
    3.45
     specialists
    1.88
     Profession
    1.88
     professional
    1.82
     practitioners
    1.81
     experts
    1.81
     clinicians
    1.68
     technicians
    1.66
     professions
    1.64
     therapists
    1.58
    Activations Density 0.010%

    No Known Activations