© 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. 10395
    Prev
    Next
    INDEX
    Explanations

    locations or buildings that hold historical or symbolic significance

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of significant buildings and structures

    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
    ãĥĥãĥī
    -0.75
    ãģĹ
    -0.66
     Spectrum
    -0.64
    Dispatch
    -0.59
    etitive
    -0.58
     Prevention
    -0.58
    itivity
    -0.57
     Lyft
    -0.57
    hitting
    -0.57
    powers
    -0.57
    POSITIVE LOGITS
     Dwell
    0.95
     courtyard
    0.92
     tower
    0.89
     entrance
    0.88
    tower
    0.85
     chapel
    0.84
    yard
    0.84
    tyard
    0.82
     erected
    0.81
     keeper
    0.81
    Activations Density 0.131%

    No Known Activations