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. 20611
    Prev
    Next
    INDEX
    Explanations

    words related to physical or emotional comfort

    oai_token-act-pair · gpt-3.5-turbo

    references to comfort and its variations

    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
     Zhu
    -0.71
     Sharma
    -0.68
     recurring
    -0.67
     permanent
    -0.65
     Klein
    -0.64
     disciplinary
    -0.62
     crawl
    -0.61
     set
    -0.61
     viral
    -0.61
     Bhar
    -0.60
    POSITIVE LOGITS
    fort
    4.70
    Fort
    1.72
    forts
    1.63
     fort
    1.41
    comfort
    1.24
    fen
    1.14
    fif
    1.13
    mont
    1.10
     Fort
    1.08
    pport
    1.07
    Activations Density 0.022%

    No Known Activations