© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4151
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating future plans or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating intentions or plans

    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
    quickShipAvailable
    -0.88
     Explan
    -0.86
    answered
    -0.84
     comprehension
    -0.77
    felt
    -0.75
    justice
    -0.73
    violent
    -0.73
    danger
    -0.72
     Resistance
    -0.71
    é»Ĵ
    -0.71
    POSITIVE LOGITS
     advertise
    1.41
     incorporate
    1.33
     integrate
    1.32
     introduce
    1.31
     allocate
    1.30
     sell
    1.30
     distribute
    1.29
     acquire
    1.29
     provide
    1.28
     invest
    1.28
    Activations Density 0.398%

    No Known Activations