© 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. 1-RES-JB
    11. 10285
    Prev
    Next
    INDEX
    Explanations

    adjectives related to intense or extreme situations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with sensationalism and militarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.81
    wine
    -0.69
     Madden
    -0.67
    rooms
    -0.67
    peak
    -0.67
    ystem
    -0.66
    tto
    -0.66
    arettes
    -0.66
     Bowl
    -0.66
    RO
    -0.65
    POSITIVE LOGITS
    ism
    1.56
    istic
    1.51
    ist
    1.37
    ists
    1.32
    istical
    1.32
    istically
    1.31
    ized
    1.27
    isms
    1.20
    izing
    1.13
    ization
    1.12
    Activations Density 0.018%

    No Known Activations