© 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. 4-RES-JB
    6. 9290
    Prev
    Next
    INDEX
    Explanations

    general terms related to people of various backgrounds or traits

    oai_token-act-pair · gpt-3.5-turbo

    references to diverse groups of people across different categories

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

    No Comments

    Negative Logits
    Quantity
    -0.75
    obin
    -0.72
    LOCK
    -0.63
     Symptoms
    -0.63
    BIL
    -0.60
     Collider
    -0.60
     extrad
    -0.60
    Quotes
    -0.60
    ATURES
    -0.59
    ãĥĥãĤ¯
    -0.59
    POSITIVE LOGITS
     sexes
    0.78
     respective
    0.72
    pires
    0.71
     backgrounds
    0.70
    conservancy
    0.69
     booths
    0.68
     Old
    0.68
    pired
    0.67
     frontline
    0.67
     alike
    0.67
    Activations Density 0.862%

    No Known Activations