© 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. 17269
    Prev
    Next
    INDEX
    Explanations

    quotes or specific highlighted text within a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotes and references to them

    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
     Kimmel
    -0.71
    aucas
    -0.70
    heastern
    -0.70
    ells
    -0.65
    etting
    -0.65
    Ļ½
    -0.65
    oche
    -0.64
    idden
    -0.63
    heast
    -0.63
    obs
    -0.63
    POSITIVE LOGITS
    Quote
    1.18
     Quote
    0.97
     Investigator
    0.93
    Hero
    0.79
    ertodd
    0.77
    Code
    0.74
    Edited
    0.72
    Maker
    0.71
    Artist
    0.70
     Originally
    0.70
    Activations Density 0.022%

    No Known Activations