© 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. 15484
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions and events involving people and objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of surveillance or video footage involving people

    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
    @#&
    -0.78
    ãĤ¦ãĤ¹
    -0.73
    needed
    -0.72
     Ratings
    -0.71
    politics
    -0.67
    Prem
    -0.65
    idays
    -0.65
    lished
    -0.64
    Sov
    -0.64
    minimum
    -0.63
    POSITIVE LOGITS
     kneeling
    1.09
     flanked
    1.01
     caption
    0.98
     silhouette
    0.97
     silhou
    0.96
     grinning
    0.95
     smiling
    0.95
     handcuffed
    0.95
     menacing
    0.93
     POV
    0.87
    Activations Density 0.534%

    No Known Activations