© 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. 23191
    Prev
    Next
    INDEX
    Explanations

    texts related to alternative scenarios or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and conjectures about hypothetical situations

    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
     extends
    -0.78
     denotes
    -0.77
     enhances
    -0.72
     determines
    -0.71
     activates
    -0.71
     applies
    -0.70
     progresses
    -0.70
     attaches
    -0.70
     depends
    -0.68
     restores
    -0.68
    POSITIVE LOGITS
    icably
    0.75
    emonium
    0.72
     still
    0.72
    ichen
    0.71
    irth
    0.71
    ERY
    0.71
    Had
    0.71
     undoubtedly
    0.69
    apest
    0.69
    yan
    0.69
    Activations Density 0.165%

    No Known Activations