© 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. 4-RES-JB
    11. 12279
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names potentially related to politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tarl" in the text

    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
    flix
    -0.85
    ndra
    -0.71
     Called
    -0.69
     Karma
    -0.69
    nder
    -0.66
     Dangerous
    -0.66
     Doct
    -0.65
    LV
    -0.64
    FFER
    -0.64
    Media
    -0.64
    POSITIVE LOGITS
    ounge
    1.09
    ophone
    1.09
    atan
    1.04
    anguage
    0.95
    ength
    0.94
    adium
    0.93
    oths
    0.90
    otta
    0.89
    volent
    0.88
    iseum
    0.87
    Activations Density 0.009%

    No Known Activations