© 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. 9-RES-JB
    11. 4110
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations with specific population or statistical data

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups and their social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delay
    -0.83
    timeout
    -0.78
     Delay
    -0.73
    Failure
    -0.73
    éĹĺ
    -0.71
     Cancel
    -0.70
    pressure
    -0.70
     delaying
    -0.70
    Leaks
    -0.70
     delay
    -0.68
    POSITIVE LOGITS
     similarities
    1.09
     ancestry
    1.00
     origins
    0.90
     resemb
    0.90
     stereotypes
    0.88
     ethnicity
    0.84
     cultures
    0.84
     nationality
    0.83
     synonymous
    0.83
     anthropology
    0.82
    Activations Density 1.378%

    No Known Activations