© 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. 3-RES-JB
    11. 10735
    Prev
    Next
    INDEX
    Explanations

    words related to light or lighting

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bid
    -0.67
    Ô
    -0.66
    interstitial
    -0.65
     overseen
    -0.63
    ħĭ
    -0.63
    aroo
    -0.62
     Cosponsors
    -0.60
     trusts
    -0.58
     Dow
    -0.58
    iard
    -0.57
    POSITIVE LOGITS
    elight
    0.78
     shine
    0.73
    ovych
    0.72
     spoilers
    0.71
     flashlight
    0.71
    oshenko
    0.69
    itiveness
    0.66
     candles
    0.66
    dark
    0.64
     vibrations
    0.63
    Activations Density 0.278%

    No Known Activations