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. 14828
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures or conditions, specifically focusing on "otomy" terms

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to various branches of biology and natural sciences

    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
    ividual
    -0.76
    posted
    -0.70
     claimants
    -0.65
    leased
    -0.62
    ileaks
    -0.62
    ivism
    -0.61
     minimized
    -0.61
     Idle
    -0.60
    paid
    -0.60
     nonpartisan
    -0.60
    POSITIVE LOGITS
    omy
    1.37
    gdala
    1.11
    olit
    0.93
    elia
    0.93
    ography
    0.90
    ograph
    0.79
    opy
    0.78
    OGR
    0.77
    ographs
    0.75
    opathy
    0.75
    Activations Density 0.007%

    No Known Activations