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. 17037
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically focusing on terms related to 'dystrophy' as well as 'abolical effectiveness'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to muscular dystrophy and related medical concepts

    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
     oats
    -0.78
    eus
    -0.64
     helic
    -0.64
     DRAG
    -0.64
     margins
    -0.60
     Austral
    -0.60
     unnecessary
    -0.58
     Ruler
    -0.58
     immersion
    -0.58
     circ
    -0.58
    POSITIVE LOGITS
    ical
    1.06
    itors
    1.01
    ptive
    1.01
    pson
    0.99
    ggles
    0.99
    efer
    0.95
    mitter
    0.95
    itable
    0.95
    umat
    0.94
    orescent
    0.92
    Activations Density 0.070%

    No Known Activations