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. 5607
    Prev
    Next
    INDEX
    Explanations

    medical terms related to surgical procedures, specifically terms related to various types of anatomical surgery

    oai_token-act-pair · gpt-3.5-turbo

    references to surgical procedures or medical terms involving "otomy."

    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
     stub
    -0.69
     138
    -0.64
     ©
    -0.63
     integrity
    -0.62
     126
    -0.60
     127
    -0.59
     125
    -0.59
     Ramadan
    -0.59
     whe
    -0.59
     spot
    -0.58
    POSITIVE LOGITS
    otom
    5.16
    otomy
    3.46
    omal
    1.17
    romy
    1.16
    ectomy
    1.12
    otrop
    1.03
    oscopic
    1.03
    osc
    1.00
    olith
    0.99
    opathic
    0.93
    Activations Density 0.015%

    No Known Activations