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. 1-RES-JB
    6. 1647
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures or treatments, particularly related to IV treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to intravenous (IV) treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    places
    -0.79
    Else
    -0.76
    journal
    -0.70
    venue
    -0.70
    boards
    -0.69
    é¾įå¥ij士
    -0.69
    place
    -0.69
    poll
    -0.68
    lopp
    -0.68
    wards
    -0.68
    POSITIVE LOGITS
     IV
    1.18
     III
    0.99
    III
    0.97
    orsi
    0.85
     helicop
    0.83
    IV
    0.83
    irtual
    0.81
    rics
    0.81
    orus
    0.80
    ISION
    0.80
    Activations Density 0.005%

    No Known Activations