© 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. 5502
    Prev
    Next
    INDEX
    Explanations

    phrases related to power and sports, such as "power-play," "power-hungry," and "power-hitting."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to power plays and their outcomes in sports contexts

    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
    Ĭ±
    -0.76
     pigeon
    -0.72
    bats
    -0.67
     seiz
    -0.66
    hospital
    -0.65
    é¾įå
    -0.65
    lish
    -0.64
    alid
    -0.63
     Nationwide
    -0.62
     condol
    -0.62
    POSITIVE LOGITS
     ignition
    0.88
     amplification
    0.87
     acceleration
    0.80
     propulsion
    0.76
     brakes
    0.76
     amplifier
    0.75
     ampl
    0.75
    ierrez
    0.73
     amps
    0.72
     levers
    0.72
    Activations Density 0.353%

    No Known Activations