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. 8-RES-JB
    6. 18171
    Prev
    Next
    INDEX
    Explanations

    medical terms related to inflammation or clinical conditions

    oai_token-act-pair · gpt-3.5-turbo

    medical terms related to various types of "itis" and inflammation conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.85
    htaking
    -0.81
    cash
    -0.80
    anamo
    -0.79
    Cash
    -0.79
    soDeliveryDate
    -0.75
    Commerce
    -0.74
    berus
    -0.73
    awei
    -0.71
    eworld
    -0.71
    POSITIVE LOGITS
     symptoms
    1.22
     Symptoms
    1.18
     syndrome
    1.15
     Syndrome
    1.12
     suff
    1.11
     mell
    1.10
     prevention
    1.04
     remission
    1.04
    ptoms
    1.03
    rosis
    1.03
    Activations Density 0.107%

    No Known Activations