© 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. 20786
    Prev
    Next
    INDEX
    Explanations

    the word "June" as a specific keyword

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dune."

    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
    loo
    -0.87
    İĭ
    -0.79
    BILITIES
    -0.78
    ivation
    -0.75
    etheless
    -0.75
    lished
    -0.74
    pread
    -0.73
    ories
    -0.72
    sonian
    -0.70
    rael
    -0.68
    POSITIVE LOGITS
    arthed
    0.97
    une
    0.76
    lected
    0.64
    lect
    0.63
    nels
    0.63
    arate
    0.63
    hill
    0.62
     Mik
    0.61
    anu
    0.61
    iban
    0.60
    Activations Density 0.012%

    No Known Activations