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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23942
    Prev
    Next
    INDEX
    Explanations

    events and specific references related to biomedical research and health science

    oai_token-act-pair · gpt-3.5-turbo

    specific biochemical compounds and their related metrics

    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
    awaru
    -0.78
    rolet
    -0.76
    amera
    -0.75
    =-=-
    -0.75
    atu
    -0.74
     Mehran
    -0.74
    onz
    -0.71
    ãĤ¹ãĥĪ
    -0.70
    vil
    -0.70
    bilt
    -0.70
    POSITIVE LOGITS
    β
    1.14
     receptor
    1.05
     inhibitors
    1.03
     enzymes
    1.00
     inhibition
    0.99
    α
    0.99
     receptors
    0.99
     inhibitor
    0.98
     protein
    0.97
     deficiency
    0.96
    Activations Density 0.109%

    No Known Activations