© 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. 3-RES-JB
    11. 23435
    Prev
    Next
    INDEX
    Explanations

    names or references to a specific individual, "Hit", potentially associated with a contentious context or critique

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Hitler."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.88
    utical
    -0.79
    pires
    -0.76
    UTH
    -0.73
    ¥µ
    -0.73
    æ°
    -0.69
    ĨĴ
    -0.66
    æ©Ł
    -0.66
    ħĭ
    -0.66
    Downloadha
    -0.66
    POSITIVE LOGITS
    chens
    1.29
    achi
    1.06
    ters
    0.95
    ched
    0.91
    ches
    0.89
    endra
    0.86
    gerald
    0.80
    gers
    0.76
    ting
    0.76
    ashi
    0.75
    Activations Density 0.019%

    No Known Activations