© 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. 11-RES-JB
    11. 3439
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an investigation or examination of a topic or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to investigations or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ranked
    -0.84
    âĹ¼
    -0.69
    illes
    -0.59
    ©
    -0.58
    Own
    -0.56
    ffe
    -0.55
    ille
    -0.55
    wcs
    -0.54
    ilts
    -0.54
    Weather
    -0.54
    POSITIVE LOGITS
     into
    1.11
     INTO
    0.86
     closely
    0.85
     forward
    0.81
     favorably
    0.77
     specifically
    0.74
    ression
    0.73
    izons
    0.72
     skept
    0.72
     carefully
    0.72
    Activations Density 0.044%

    No Known Activations