© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4248
    Prev
    Next
    INDEX
    Explanations

    instances where the word "White" appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "White."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITAL
    -0.85
    cffffcc
    -0.80
    udeau
    -0.77
    Downloadha
    -0.77
    ategory
    -0.75
    REM
    -0.72
    yrinth
    -0.72
    INGTON
    -0.70
    =-=-
    -0.70
    ension
    -0.69
    POSITIVE LOGITS
    caps
    1.11
    beard
    1.09
    horse
    1.09
    house
    1.08
     Sox
    1.06
    hall
    1.03
     supremacist
    1.01
    bread
    1.01
    houses
    1.00
     supremacists
    1.00
    Activations Density 0.028%

    No Known Activations