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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10558
    Prev
    Next
    INDEX
    Explanations

    nouns related to physical and psychological aspects of health and well-being

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate physical and emotional conditions or health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decay
    -0.83
     Shadows
    -0.77
     oranges
    -0.76
     Hera
    -0.75
    cakes
    -0.74
     Awakens
    -0.73
    France
    -0.70
     Ud
    -0.70
    opia
    -0.67
    uffs
    -0.67
    POSITIVE LOGITS
     psychological
    1.44
     physiological
    1.41
     linguistic
    1.38
     philosophical
    1.34
     behavioral
    1.33
     metaphysical
    1.32
     behavioural
    1.30
     logistical
    1.30
     biological
    1.29
     spiritual
    1.26
    Activations Density 0.239%

    No Known Activations