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. 7-RES-JB
    6. 16657
    Prev
    Next
    INDEX
    Explanations

    emotions and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and quantitative observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colonial
    -0.48
     veto
    -0.48
    Tax
    -0.47
     lymph
    -0.47
     Penal
    -0.47
    天
    -0.46
    mone
    -0.46
     cartoon
    -0.46
    act
    -0.45
     Refugee
    -0.45
    POSITIVE LOGITS
     nonetheless
    0.85
     anyway
    0.74
    awaru
    0.74
     anyways
    0.72
     moreover
    0.63
     altogether
    0.62
     encompasses
    0.61
     proport
    0.60
    EEE
    0.58
     overwhel
    0.58
    Activations Density 1.186%

    No Known Activations