© 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. 22535
    Prev
    Next
    INDEX
    Explanations

    instances where a statement or phrase is followed by an elaboration or explanation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that said," indicating transitions or qualifications in statements

    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
    prus
    -0.82
    Desktop
    -0.74
    Bug
    -0.72
    Tai
    -0.72
    ItemImage
    -0.71
     Tablet
    -0.71
    Feature
    -0.69
    Street
    -0.69
    MEN
    -0.66
    Jews
    -0.64
    POSITIVE LOGITS
    sonian
    0.79
    itivity
    0.66
     Blank
    0.64
     goodbye
    0.64
    rescent
    0.62
    ickson
    0.62
     anecd
    0.60
     culmin
    0.58
     intentions
    0.56
     Cooke
    0.56
    Activations Density 0.058%

    No Known Activations