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. 11-RES-JB
    6. 9797
    Prev
    Next
    INDEX
    Explanations

    gatherings or crowds of people along with numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to large gatherings of people

    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
    terms
    -0.86
    pring
    -0.83
    inates
    -0.78
    agate
    -0.78
     Pwr
    -0.74
    inventoryQuantity
    -0.72
    peria
    -0.71
     downgrade
    -0.71
    zu
    -0.69
    hiro
    -0.68
    POSITIVE LOGITS
     onlook
    1.54
     spectators
    1.41
     cheering
    1.39
     demonstrators
    1.36
     protesters
    1.33
     protestors
    1.30
     attendees
    1.27
     supporters
    1.26
     bystanders
    1.13
     passers
    1.10
    Activations Density 0.300%

    No Known Activations