© 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. 1-RES-JB
    11. 20036
    Prev
    Next
    INDEX
    Explanations

    instances of the word "light", typically in the context of a descriptor or a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isner
    -0.70
    irl
    -0.67
     critically
    -0.67
    apons
    -0.66
    ettings
    -0.64
     deleg
    -0.64
    CVE
    -0.63
    ALD
    -0.62
     notor
    -0.60
     whole
    -0.60
    POSITIVE LOGITS
    lights
    1.33
    light
    1.31
    enment
    1.10
    lighting
    0.97
    aber
    0.89
    moon
    0.88
    weights
    0.87
    ened
    0.80
    Light
    0.79
    tenance
    0.78
    Activations Density 0.006%

    No Known Activations