© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by descriptions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate what entities are known for certain characteristics or actions

    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
    soever
    -0.94
    Reviewed
    -0.74
    Next
    -0.72
    MRI
    -0.71
    ixon
    -0.70
    INFO
    -0.69
    nown
    -0.69
    down
    -0.68
    Report
    -0.68
    enter
    -0.67
    POSITIVE LOGITS
     having
    1.00
     producing
    0.94
     being
    0.91
     invent
    0.90
     creating
    0.89
     daring
    0.89
    geries
    0.87
     crafting
    0.85
     delivering
    0.85
     cracking
    0.84
    Activations Density 0.098%

    No Known Activations