© 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. 1-RES-JB
    11. 2643
    Prev
    Next
    INDEX
    Explanations

    mentions of "botanical" or "botanical interests."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of bots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trib
    -0.69
    Rated
    -0.67
    rising
    -0.67
    dress
    -0.67
     Situation
    -0.62
    Demand
    -0.62
     Witness
    -0.61
     Declaration
    -0.61
     Truth
    -0.61
     Pilgrim
    -0.60
    POSITIVE LOGITS
    anical
    1.33
     bot
    1.25
     Bot
    1.05
    anie
    0.97
    anooga
    0.91
    anic
    0.91
    apons
    0.89
    cham
    0.87
    orde
    0.86
    assium
    0.82
    Activations Density 0.006%

    No Known Activations