© 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. 0-RES-JB
    11. 13116
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology or equipment used for communication

    oai_token-act-pair · gpt-3.5-turbo

    references to cable television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarn
    -0.90
     Wei
    -0.73
     Kop
    -0.73
    haus
    -0.73
     Manz
    -0.67
    rika
    -0.66
     âĸº
    -0.66
    Û
    -0.66
    roth
    -0.65
     Zan
    -0.64
    POSITIVE LOGITS
     cable
    3.81
     cables
    2.80
     Cable
    2.78
     cord
    1.69
     wires
    1.55
     Comcast
    1.47
     wire
    1.42
     cords
    1.35
     wireless
    1.35
     broadband
    1.27
    Activations Density 0.012%

    No Known Activations