© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13350
    Prev
    Next
    INDEX
    Explanations

    mentions or references to activities or events happening in the physical world outside of the online or digital realm

    oai_token-act-pair · gpt-3.5-turbo

    references to offline activities or elements

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

    No Comments

    Negative Logits
    owitz
    -0.91
    atorial
    -0.85
    geries
    -0.84
    azaki
    -0.82
    usky
    -0.82
    ayn
    -0.82
    coni
    -0.82
    endish
    -0.81
    icles
    -0.81
    aire
    -0.79
    POSITIVE LOGITS
     offline
    0.75
    spection
    0.69
     computing
    0.66
     standby
    0.66
     storefront
    0.65
     Grid
    0.64
     multiplayer
    0.64
    phrine
    0.63
     maintenance
    0.62
     calcul
    0.62
    Activations Density 0.009%

    No Known Activations