© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    assertive statements or claims within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate claims or statements about specific events or actions

    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
    english
    -0.84
    Laughs
    -0.82
    byss
    -0.81
    register
    -0.79
    rex
    -0.76
    vc
    -0.76
    mmmm
    -0.75
    utical
    -0.74
    erenn
    -0.73
    EStream
    -0.73
    POSITIVE LOGITS
     they
    0.88
     ousted
    0.85
     Saddam
    0.83
     he
    0.82
     hackers
    0.82
     Barack
    0.79
     millions
    0.78
     President
    0.77
     she
    0.76
     Hillary
    0.75
    Activations Density 0.217%

    No Known Activations