© 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. 10-RES-JB
    11. 11619
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for intervention

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or requests for initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cong
    -0.79
    Bey
    -0.70
    die
    -0.69
    tch
    -0.68
    dot
    -0.66
    hung
    -0.65
    ertodd
    -0.65
    Fest
    -0.63
     fest
    -0.63
    gian
    -0.62
    POSITIVE LOGITS
     steps
    1.24
     heed
    1.20
     precautions
    1.20
     corrective
    1.14
     measures
    1.13
     precaution
    1.11
     action
    1.10
     advantage
    1.09
     Steps
    1.08
     proactive
    1.04
    Activations Density 0.092%

    No Known Activations