© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15191
    Prev
    Next
    INDEX
    Explanations

    concepts related to the physics of light and its interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to light and its properties

    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
    ettings
    -0.82
    halla
    -0.74
    TAIN
    -0.73
    CVE
    -0.72
    insula
    -0.71
    lished
    -0.70
    ocamp
    -0.69
    llah
    -0.69
    PsyNetMessage
    -0.69
    berus
    -0.68
    POSITIVE LOGITS
     bulbs
    1.12
     rays
    1.05
    nings
    1.05
     bulb
    1.04
    bul
    0.95
     emitting
    0.93
     microsc
    0.93
    eners
    0.92
    beam
    0.91
    ening
    0.91
    Activations Density 0.032%

    No Known Activations