© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2591
    Prev
    Next
    INDEX
    Explanations

    phrases containing the sequence "gu"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the letters "gu" in the text

    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
    cling
    -0.82
    hower
    -0.72
     Spectrum
    -0.68
    geist
    -0.67
    croft
    -0.66
    ŃĶ
    -0.65
     spaced
    -0.64
     womb
    -0.61
     plank
    -0.59
     centrif
    -0.59
    POSITIVE LOGITS
    inea
    1.24
    ilty
    1.20
    idelines
    1.18
    arding
    1.15
    pta
    1.14
    cci
    1.13
    bernatorial
    1.12
    arant
    1.12
    errilla
    1.11
    ests
    1.10
    Activations Density 0.021%

    No Known Activations