© 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. 0-RES-JB
    11. 19131
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense emotional reactions or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of spasms in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     owned
    -0.70
     Ground
    -0.65
     FD
    -0.64
     owners
    -0.64
     preventive
    -0.63
     Progressive
    -0.61
     planned
    -0.61
     FSA
    -0.60
     Crown
    -0.60
     Seat
    -0.60
    POSITIVE LOGITS
    asm
    4.78
    asms
    2.73
    asma
    1.89
    astically
    1.44
    astic
    1.23
    astics
    1.10
    ast
    0.98
    asts
    0.95
    iasm
    0.95
    asia
    0.94
    Activations Density 0.025%

    No Known Activations