© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    references to people and their abilities or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to healthcare coverage and accessibility issues

    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
    scene
    -0.82
    Dialogue
    -0.81
     Starr
    -0.76
     onstage
    -0.71
     teasing
    -0.71
    OLOG
    -0.71
     Creep
    -0.71
     SCP
    -0.70
     Vaj
    -0.70
    ĸļ
    -0.70
    POSITIVE LOGITS
     consume
    1.20
     buy
    1.11
     migrate
    1.10
     purchase
    1.10
     subsid
    1.08
     afford
    1.03
     rely
    1.00
     purchasing
    0.99
     commute
    0.97
     enjoy
    0.97
    Activations Density 0.481%

    No Known Activations