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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21720
    Prev
    Next
    INDEX
    Explanations

    words related to being filled with something

    oai_token-act-pair · gpt-3.5-turbo

    words associated with being filled or packed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minor
    -0.65
     moot
    -0.61
     precedent
    -0.61
     Car
    -0.60
     decentral
    -0.60
     minimum
    -0.60
     Das
    -0.59
     Mechan
    -0.59
     turnover
    -0.59
     TA
    -0.59
    POSITIVE LOGITS
    filled
    4.00
    packed
    2.01
    laden
    1.81
    fill
    1.77
    ridden
    1.63
    lined
    1.50
    loaded
    1.40
    covered
    1.38
    stained
    1.34
     filled
    1.11
    Activations Density 0.023%

    No Known Activations