© 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. 10-RES-JB
    6. 2249
    Prev
    Next
    INDEX
    Explanations

    text passages featuring the word "here" to indicate a critical point or issue being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant point or takeaway in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parap
    -0.70
    ews
    -0.65
     Doors
    -0.64
    rily
    -0.57
     Gujar
    -0.57
    THER
    -0.57
    urated
    -0.55
    ams
    -0.54
    eer
    -0.54
    visors
    -0.53
    POSITIVE LOGITS
    abouts
    1.45
    tics
    1.41
    tical
    1.37
    tic
    1.12
     guiActiveUn
    0.76
    with
    0.75
    upon
    0.75
    after
    0.75
    from
    0.72
    otomy
    0.71
    Activations Density 0.052%

    No Known Activations