© 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. 19637
    Prev
    Next
    INDEX
    Explanations

    the term "indie" associated with various subjects like movies, music, rockers, artists, developers, books, and wrestling

    oai_token-act-pair · gpt-3.5-turbo

    references to indie culture and its related elements

    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
    xual
    -0.81
    atche
    -0.79
    aukee
    -0.74
    ciating
    -0.73
    idon
    -0.73
    oran
    -0.71
    anism
    -0.70
    hner
    -0.69
    cific
    -0.69
    midt
    -0.68
    POSITIVE LOGITS
     darling
    0.89
    unic
    0.83
     minded
    0.81
     indie
    0.81
    venture
    0.80
     filmmaking
    0.75
     folk
    0.74
    esc
    0.73
    spective
    0.71
     cottage
    0.68
    Activations Density 0.016%

    No Known Activations