Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19818
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'light' or related terms such as 'Lights', often within a spiritual or metaphorical context

    oai_token-act-pair · gpt-3.5-turbo

    references to "Light" and its associated concepts

    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
    ij士
    -0.86
    PsyNetMessage
    -0.82
    llah
    -0.72
    çīĪ
    -0.72
    ä½ľ
    -0.68
    CVE
    -0.68
    ODUCT
    -0.68
     Boko
    -0.67
    ersion
    -0.67
    ettings
    -0.66
    POSITIVE LOGITS
    light
    1.06
    bringer
    1.00
     Light
    1.00
    hearted
    0.97
    lights
    0.95
     bulb
    0.92
    weight
    0.90
    aber
    0.90
    ening
    0.89
    Light
    0.89
    Activations Density 0.009%

    No Known Activations