© 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. 8-RES-JB
    11. 1182
    Prev
    Next
    INDEX
    Explanations

    the word "one" as a common denominator

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •all features

    No Comments

    Negative Logits
    oof
    -0.67
     actionGroup
    -0.67
    ooks
    -0.66
    ories
    -0.65
    akings
    -0.64
    osponsors
    -0.64
    emies
    -0.63
    photos
    -0.63
    thumbnails
    -0.62
    actions
    -0.62
    POSITIVE LOGITS
     hundred
    1.01
     wonders
    0.93
     assumes
    0.90
     thousand
    0.87
     Hundred
    0.87
     thing
    0.84
     learns
    0.79
     glance
    0.76
     cannot
    0.75
     sided
    0.74
    Activations Density 0.122%

    No Known Activations