© 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. 6-RES-JB
    11. 3732
    Prev
    Next
    INDEX
    Explanations

    words related to swarming or clustering

    oai_token-act-pair · gpt-3.5-turbo

    references to swarms of jellyfish and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uz
    -0.72
    issance
    -0.71
     vested
    -0.69
     guarant
    -0.65
    iant
    -0.65
    encing
    -0.62
    psons
    -0.61
    soDeliveryDate
    -0.61
    ãĥ¼ãĥ³
    -0.60
     Accountability
    -0.59
    POSITIVE LOGITS
    craft
    0.90
    bean
    0.88
    ular
    0.83
    orne
    0.76
    warts
    0.76
    lets
    0.76
    wart
    0.73
    vana
    0.72
    bees
    0.71
    cules
    0.71
    Activations Density 0.023%

    No Known Activations