© 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. 4-RES-JB
    11. 8563
    Prev
    Next
    INDEX
    Explanations

    descriptions and mentions of comets

    oai_token-act-pair · gpt-3.5-turbo

    references to comets

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

    No Comments

    Negative Logits
    dos
    -0.80
    skirts
    -0.78
    antha
    -0.74
    Hispanic
    -0.69
    lasses
    -0.68
    aceutical
    -0.68
     Eston
    -0.67
    otics
    -0.67
     Protestant
    -0.67
    radical
    -0.66
    POSITIVE LOGITS
     comet
    1.03
     nucleus
    0.86
     Ping
    0.86
     crater
    0.74
     Comet
    0.72
     Galileo
    0.69
     tails
    0.69
     orbiting
    0.68
     Nebula
    0.67
     crust
    0.66
    Activations Density 0.012%

    No Known Activations