© 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. 8-RES-JB
    11. 17184
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of service or servitude

    oai_token-act-pair · gpt-3.5-turbo

    terms related to service or servitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kubrick
    -0.70
     Pound
    -0.62
     Sands
    -0.62
     Revised
    -0.62
     highlighting
    -0.62
    olson
    -0.60
     heavier
    -0.58
    hedral
    -0.57
     prone
    -0.57
    ãĥ£
    -0.57
    POSITIVE LOGITS
    iced
    1.22
    serv
    1.02
    itude
    1.02
    icing
    1.00
    maid
    0.97
    ility
    0.90
    iments
    0.89
    icer
    0.86
    itors
    0.86
    icable
    0.85
    Activations Density 0.026%

    No Known Activations