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. 0-RES-JB
    6. 17100
    Prev
    Next
    INDEX
    Explanations

    mention of physical pain and pain medication

    oai_token-act-pair · gpt-3.5-turbo

    references to pain and its impact on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erd
    -0.79
    ETF
    -0.72
    arent
    -0.70
    atellite
    -0.69
    arthed
    -0.69
    campaign
    -0.68
    wich
    -0.67
    =>
    -0.66
    tower
    -0.66
    adan
    -0.65
    POSITIVE LOGITS
     pain
    3.77
     Pain
    2.43
    pain
    2.37
    Pain
    2.18
     agony
    2.10
     pains
    2.06
     headache
    1.68
     analges
    1.67
     anguish
    1.65
     painful
    1.64
    Activations Density 0.018%

    No Known Activations