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. 8-RES-JB
    6. 18776
    Prev
    Next
    INDEX
    Explanations

    sentences expressing optimism or excitement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pour
    -0.57
     periodically
    -0.57
     corpus
    -0.57
     incrim
    -0.56
     Leilan
    -0.55
     contact
    -0.55
     recept
    -0.55
    ixel
    -0.55
    lie
    -0.54
     appl
    -0.54
    POSITIVE LOGITS
    quickShipAvailable
    0.67
    efe
    0.64
    STEM
    0.60
    ł
    0.58
    cedented
    0.58
     CES
    0.54
    razy
    0.54
     coincidence
    0.54
     worse
    0.52
     clearer
    0.52
    Activations Density 0.256%

    No Known Activations