© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    specific phrases that involve being a part of something or a specific action being a part of a larger context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as part of" in various contexts

    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
     hither
    -0.72
    oir
    -0.70
    istas
    -0.65
    ants
    -0.62
    iste
    -0.61
    usercontent
    -0.61
    ihu
    -0.60
    quit
    -0.59
    lah
    -0.59
    eers
    -0.59
    POSITIVE LOGITS
     preparations
    1.00
     broader
    0.92
    Operation
    0.87
     ongoing
    0.87
     wider
    0.84
     Operation
    0.83
     efforts
    0.81
     its
    0.75
     precaution
    0.73
     widening
    0.72
    Activations Density 0.132%

    No Known Activations