© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22479
    Prev
    Next
    INDEX
    Explanations

    words related to occupation or occupancy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to occupancy and the actions of occupants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verbal
    -0.78
    peer
    -0.73
    cale
    -0.69
    cond
    -0.67
    critical
    -0.66
    ripp
    -0.65
    vous
    -0.65
     leukemia
    -0.65
    fire
    -0.64
     Cay
    -0.64
    POSITIVE LOGITS
     occupying
    1.12
     occup
    1.07
     occupancy
    1.01
     occupy
    0.95
    iture
    0.85
     occupation
    0.82
     occupants
    0.78
     occupations
    0.78
    ucha
    0.77
     occupies
    0.77
    Activations Density 0.010%

    No Known Activations