© 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 EvalsExportsinterp-engineNEWAPI 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. 15420
    Prev
    Next
    INDEX
    Explanations

    occupations ending in the suffix "-ist"

    oai_token-act-pair · gpt-3.5-turbo

    words that denote a person's profession or role

    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
    AGES
    -0.57
     adults
    -0.57
     improper
    -0.56
     certify
    -0.55
     ammonia
    -0.54
     probable
    -0.53
     halftime
    -0.53
     babies
    -0.52
     HAL
    -0.52
    fresh
    -0.52
    POSITIVE LOGITS
    ist
    4.27
    ists
    3.32
    IST
    2.56
    istic
    2.53
    ism
    2.42
    isted
    2.20
    istically
    2.12
    iste
    2.03
    ista
    1.94
    isting
    1.93
    Activations Density 0.024%

    No Known Activations