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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22331
    Prev
    Next
    INDEX
    Explanations

    LED-related terms and technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to LED technology and its specifications

    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
     Tro
    -0.70
     Webster
    -0.65
     trusts
    -0.65
     Strauss
    -0.64
    psons
    -0.64
     plural
    -0.63
    ienne
    -0.63
    rank
    -0.63
    heim
    -0.63
    polit
    -0.63
    POSITIVE LOGITS
     LED
    3.65
     LEDs
    3.21
    LED
    2.75
     LCD
    2.09
     OLED
    1.94
     Arduino
    1.49
     RGB
    1.36
     lamps
    1.32
     fluorescent
    1.32
     Lighting
    1.31
    Activations Density 0.016%

    No Known Activations