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. 23274
    Prev
    Next
    INDEX
    Explanations

    instances of people lying down or being in a prone position

    oai_token-act-pair · gpt-3.5-turbo

    instances of people lying or positioned in various ways

    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
     Flavoring
    -0.82
    ãĥķãĤ©
    -0.80
    allo
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    ãĥĪ
    -0.73
    sylv
    -0.73
    ãĥ©ãĥ³
    -0.72
    ocy
    -0.71
    ormons
    -0.71
     Cosponsors
    -0.70
    POSITIVE LOGITS
     slumped
    1.11
     beside
    1.11
     kneeling
    1.00
     crou
    0.99
     seiz
    0.99
     comfortably
    0.96
     asleep
    0.95
     unconscious
    0.94
     peacefully
    0.93
     clutching
    0.92
    Activations Density 0.145%

    No Known Activations