© 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. 0-RES-JB
    11. 15051
    Prev
    Next
    INDEX
    Explanations

    terms related to integration or being combined into a single entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "integrated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raise
    -0.75
     Celeb
    -0.75
    reck
    -0.72
     coughing
    -0.68
    <?
    -0.68
    berries
    -0.67
     Picks
    -0.66
     Cruel
    -0.65
     Thrones
    -0.65
     Nay
    -0.65
    POSITIVE LOGITS
     integrated
    3.41
     integrate
    2.20
     integrating
    2.14
     integration
    2.11
     Integrated
    2.06
     integ
    1.80
     Integration
    1.77
    Integ
    1.76
     integrates
    1.74
    integ
    1.67
    Activations Density 0.011%

    No Known Activations