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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5401
    Prev
    Next
    INDEX
    Explanations

    mentions of various aspects of light, such as illumination, wavelengths, and absorption

    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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.86
    ettings
    -0.79
    TAIN
    -0.72
    sburgh
    -0.71
    PsyNetMessage
    -0.70
    halla
    -0.68
    insula
    -0.65
    ocamp
    -0.64
    ht
    -0.63
     Rough
    -0.63
    POSITIVE LOGITS
     bulbs
    0.96
    nings
    0.95
     emitted
    0.92
     rays
    0.92
     emitting
    0.91
     bulb
    0.91
    enment
    0.89
    eners
    0.86
     photons
    0.82
    speed
    0.82
    Activations Density 0.027%

    No Known Activations