© 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. 9-RES-JB
    11. 7352
    Prev
    Next
    INDEX
    Explanations

    phrases related to decisions or actions of staying or keeping something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to maintaining or continuing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reporter
    -0.74
    alion
    -0.73
    edia
    -0.73
    ĸļ
    -0.73
    ongyang
    -0.71
    worm
    -0.71
    arted
    -0.69
    onut
    -0.67
    tip
    -0.65
    icular
    -0.65
    POSITIVE LOGITS
     indefinitely
    0.94
     altogether
    0.80
     permanently
    0.79
     outright
    0.77
     unilaterally
    0.77
     moratorium
    0.76
     shel
    0.76
     administr
    0.76
     afloat
    0.75
     stalled
    0.73
    Activations Density 0.350%

    No Known Activations