© 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. 748
    Prev
    Next
    INDEX
    Explanations

    adverbs that denote a degree or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantity or degrees of something, especially using the words "a bit," "a few," or similar constructions

    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
    ROR
    -0.69
    ãĥį
    -0.67
    ALSE
    -0.66
     Phi
    -0.64
    ãĥĩ
    -0.64
    ãĤ¨ãĥ«
    -0.64
    aired
    -0.63
     Said
    -0.62
     Anarchy
    -0.62
    uminati
    -0.60
    POSITIVE LOGITS
    ricular
    0.75
    omical
    0.72
    ivid
    0.67
    maxwell
    0.65
    ictive
    0.65
    én
    0.64
    urnal
    0.62
    leans
    0.61
    imilar
    0.61
    cerning
    0.61
    Activations Density 0.094%

    No Known Activations