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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2843
    Prev
    Next
    INDEX
    Explanations

    terms related to botany or the word "bot"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bot" or related terms in various contexts

    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
     Institution
    -0.68
    ׾
    -0.66
     Vie
    -0.61
    ITED
    -0.61
     Piercing
    -0.61
     Sporting
    -0.59
     Barg
    -0.59
     Cheong
    -0.59
     Borough
    -0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.58
    POSITIVE LOGITS
    anical
    1.74
    anic
    1.35
    any
    1.35
    nets
    1.24
    cham
    1.23
    ania
    1.15
    anooga
    1.09
    ches
    1.05
    chers
    1.02
    anos
    1.01
    Activations Density 0.030%

    No Known Activations