© 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. 6-RES-JB
    11. 9245
    Prev
    Next
    INDEX
    Explanations

    the word "the."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "watch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.75
    ucl
    -0.74
    uti
    -0.71
    ccoli
    -0.69
    recy
    -0.69
    eno
    -0.67
    iev
    -0.66
    manship
    -0.65
    trl
    -0.65
    aspberry
    -0.65
    POSITIVE LOGITS
     same
    1.28
     entirety
    1.15
     entire
    1.15
     slightest
    1.14
     latest
    1.11
     smallest
    1.10
     whole
    1.07
    ses
    0.99
     aftermath
    0.98
     vast
    0.98
    Activations Density 0.402%

    No Known Activations