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. 11-RES-JB
    6. 16906
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms, such as molecular structure, electrical current, and frequency

    oai_token-act-pair · gpt-3.5-turbo

    scientific concepts related to physical properties and behaviors of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rists
    -0.79
    obiles
    -0.74
    solete
    -0.73
    cigarettes
    -0.73
    Myth
    -0.70
    friends
    -0.70
    ebook
    -0.70
    recated
    -0.70
    gallery
    -0.69
    word
    -0.69
    POSITIVE LOGITS
     density
    1.45
     temperature
    1.35
     pH
    1.33
     thickness
    1.31
     humidity
    1.28
     amplitude
    1.27
     wavelength
    1.26
     concentration
    1.25
     composition
    1.23
     diameter
    1.23
    Activations Density 0.278%

    No Known Activations