© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    Terms related to technology and information technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to essential qualities or characteristics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     flats
    -0.55
     torped
    -0.52
    ifles
    -0.52
     needles
    -0.52
     toes
    -0.52
    quickShipAvailable
    -0.51
    unts
    -0.51
     levers
    -0.50
     receptors
    -0.48
     vents
    -0.48
    POSITIVE LOGITS
    onian
    0.60
    capitalist
    0.60
    artisan
    0.60
    sonian
    0.56
    visory
    0.56
    centric
    0.54
    nian
    0.53
    budget
    0.52
    operative
    0.52
    ennial
    0.52
    Activations Density 1.028%

    No Known Activations