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. 3-RES-JB
    6. 14854
    Prev
    Next
    INDEX
    Explanations

    terms related to natural disasters like tsunamis and medical conditions like hypothalamus

    oai_token-act-pair · gpt-3.5-turbo

    references to thermodynamics and tsunami events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lomb
    -0.78
     Archdemon
    -0.75
     Mour
    -0.74
     Riders
    -0.74
     Undead
    -0.73
     Spending
    -0.71
     Postal
    -0.70
     Medicaid
    -0.70
    _>
    -0.68
     Grimes
    -0.67
    POSITIVE LOGITS
     ther
    1.10
    ön
    0.91
    aton
    0.85
    aband
    0.84
    riter
    0.82
    anos
    0.82
    rha
    0.82
     mathemat
    0.80
    apist
    0.80
    mosp
    0.80
    Activations Density 0.007%

    No Known Activations