© 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. 2-RES-JB
    11. 17118
    Prev
    Next
    INDEX
    Explanations

    words related to living in or occupying a certain place

    oai_token-act-pair · gpt-3.5-turbo

    terms related to living beings or entities residing in a particular space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ripp
    -0.86
    20439
    -0.77
    heet
    -0.77
    iem
    -0.72
    MED
    -0.71
    sonian
    -0.70
    enic
    -0.69
    jer
    -0.68
    IFF
    -0.68
    med
    -0.68
    POSITIVE LOGITS
     inhabit
    1.01
     inhab
    0.97
     dwell
    0.93
     inhabited
    0.89
     dwelling
    0.85
     inhabitants
    0.84
     Torment
    0.83
     Hawai
    0.80
     Siege
    0.75
     Dwell
    0.74
    Activations Density 0.016%

    No Known Activations