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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 11588
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'bot'

    oai_token-act-pair · gpt-3.5-turbo

    references to bots and bot-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barg
    -0.65
     Institution
    -0.63
    dress
    -0.61
     Trib
    -0.60
    mble
    -0.60
     Piercing
    -0.59
     Vie
    -0.58
    ׾
    -0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.57
     jerk
    -0.56
    POSITIVE LOGITS
    anical
    1.74
    anic
    1.33
    any
    1.26
    ania
    1.16
    cham
    1.16
    nets
    1.07
    ulin
    1.01
    herer
    1.00
    zeb
    0.98
    anie
    0.97
    Activations Density 0.019%

    No Known Activations