© 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. 7-RES-JB
    11. 347
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "handshake"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "sh" followed by other letters or words indicating the topic of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numbered
    -0.81
     Luther
    -0.67
     Homo
    -0.63
     Ajax
    -0.63
     Nazis
    -0.63
     NEO
    -0.61
    STER
    -0.60
     Leilan
    -0.59
    ERN
    -0.58
     appellant
    -0.57
    POSITIVE LOGITS
    ackle
    1.15
    tml
    1.11
    uffle
    1.07
    apes
    1.06
    rimp
    1.06
    adows
    1.05
    anks
    1.04
    attering
    1.04
    atters
    1.03
    apesh
    1.03
    Activations Density 0.021%

    No Known Activations