Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 904
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical settings, such as clinical trials and clinical practice

    oai_token-act-pair · gpt-3.5-turbo

    terms related to clinical settings or clinical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uble
    -0.79
    ãĥĺ
    -0.77
    atto
    -0.70
    Dick
    -0.67
    hens
    -0.66
    WARD
    -0.66
     Heist
    -0.66
    imo
    -0.65
    ERC
    -0.65
    gat
    -0.65
    POSITIVE LOGITS
     trials
    0.92
     practition
    0.87
     practitioners
    0.85
    Tri
    0.81
     diagnoses
    0.81
     evaluations
    0.79
     practitioner
    0.79
     examination
    0.77
     diagnosis
    0.77
    tri
    0.77
    Activations Density 0.015%

    No Known Activations