© 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. 11-RES-JB
    11. 4766
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or activities, particularly those involving outdoor settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" occurring 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
    alogy
    -0.69
     certs
    -0.69
    emis
    -0.66
     endors
    -0.64
    tal
    -0.63
    heet
    -0.63
    acer
    -0.63
    Voice
    -0.62
    killed
    -0.61
    ãĥīãĥ©
    -0.61
    POSITIVE LOGITS
     bed
    1.08
     solitude
    1.04
     front
    1.03
     lieu
    0.92
     cramped
    0.91
     darkened
    0.89
    between
    0.89
     motel
    0.87
     silence
    0.87
     bedrooms
    0.86
    Activations Density 0.219%

    No Known Activations