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. 0-RES-JB
    6. 23813
    Prev
    Next
    INDEX
    Explanations

    words related to cloth, specifically blankets

    oai_token-act-pair · gpt-3.5-turbo

    multiple references to the word "blanket" in various contexts

    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
    rez
    -0.78
    ymes
    -0.74
    cal
    -0.70
    Gal
    -0.70
    Cal
    -0.69
    ends
    -0.69
    igr
    -0.68
     Development
    -0.68
    lycer
    -0.67
    ago
    -0.66
    POSITIVE LOGITS
     blanket
    4.11
     blankets
    2.57
     shroud
    1.33
     pillow
    1.29
     mattress
    1.25
     Blank
    1.21
     sweater
    1.20
     carpet
    1.18
     umbrella
    1.17
     cloak
    1.15
    Activations Density 0.015%

    No Known Activations