© 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. 7-RES-JB
    11. 2036
    Prev
    Next
    INDEX
    Explanations

    keywords related to research and investigation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "research" and related terms indicating investigation or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.79
    cakes
    -0.66
     promise
    -0.63
    twitch
    -0.63
     welcome
    -0.63
     warm
    -0.61
    hold
    -0.61
    Cry
    -0.60
    -+
    -0.59
    Control
    -0.59
    POSITIVE LOGITS
     researching
    1.01
     researched
    0.94
    geist
    0.81
     beforehand
    0.80
    spection
    0.80
     uncovered
    0.78
     diligently
    0.77
     uncover
    0.74
    tesy
    0.74
    nsics
    0.73
    Activations Density 0.165%

    No Known Activations