© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 20324
    Prev
    Next
    INDEX
    Explanations

    phrases related to gatherings or events where people come together

    oai_token-act-pair · gpt-3.5-turbo

    instances of collective gatherings or assemblies

    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
     Syndrome
    -0.66
    nik
    -0.65
     downgrade
    -0.62
     discontin
    -0.61
    lier
    -0.61
    phas
    -0.60
     termination
    -0.60
    ney
    -0.59
    inance
    -0.58
    rog
    -0.58
    POSITIVE LOGITS
     gathered
    3.46
     gather
    2.18
     gathers
    2.02
     assembled
    2.00
     gathering
    1.93
     collected
    1.83
     amassed
    1.64
     convened
    1.45
     Gathering
    1.39
     rallied
    1.29
    Activations Density 0.018%

    No Known Activations