© 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 EvalsExportsAPI 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. 7974
    Prev
    Next
    INDEX
    Explanations

    numerical values formatted with periods and digits

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements, particularly related to time and quantities

    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
    ÄŁ
    -0.77
    anners
    -0.75
    ournal
    -0.72
    rities
    -0.68
    ources
    -0.68
    urches
    -0.67
    heast
    -0.65
    olis
    -0.65
    quickShipAvailable
    -0.65
    anned
    -0.65
    POSITIVE LOGITS
     pity
    0.70
     Draco
    0.70
     aperture
    0.68
     knob
    0.61
     PCIe
    0.60
     TAMADRA
    0.60
     Coffin
    0.58
     Gujar
    0.58
     antenna
    0.57
     antioxid
    0.57
    Activations Density 0.375%

    No Known Activations