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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2833
    Prev
    Next
    INDEX
    Explanations

    pairs of people collaborating or working together

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts, indicating connections or relationships between subjects

    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
    wcs
    -0.90
    Contents
    -0.73
    different
    -0.71
    caps
    -0.70
    places
    -0.70
    Recomm
    -0.69
    Deal
    -0.68
    CPU
    -0.67
    é¾įåĸļ士
    -0.66
    depending
    -0.66
    POSITIVE LOGITS
     Associates
    1.22
     colleagues
    1.17
     Sons
    1.08
     others
    0.97
     colleague
    0.87
     pals
    0.86
    rogens
    0.85
    ERSON
    0.85
     fellow
    0.83
     collaborators
    0.82
    Activations Density 0.122%

    No Known Activations