© 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. 8-RES-JB
    11. 2255
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate the completion or conclusion of a thought or article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     displacement
    -0.77
     rupture
    -0.73
     diseng
    -0.73
     temperament
    -0.73
     unatt
    -0.72
     retracted
    -0.70
     posture
    -0.69
     enrol
    -0.69
     susceptibility
    -0.68
     minim
    -0.67
    POSITIVE LOGITS
     Anyway
    1.42
     ðŁĻĤ
    1.39
     Hopefully
    1.34
     :)
    1.31
     ;)
    1.30
     Please
    1.29
     Basically
    1.26
     THANK
    1.24
    Anyway
    1.23
     Thankfully
    1.21
    Activations Density 0.390%

    No Known Activations