© 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. 4-RES-JB
    11. 22295
    Prev
    Next
    INDEX
    Explanations

    words related to specific places or monuments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to historical or cultural significance

    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
    GV
    -0.68
    options
    -0.64
    ello
    -0.64
    jab
    -0.62
    nir
    -0.61
    ucket
    -0.61
    Bit
    -0.60
     impuls
    -0.60
    Zip
    -0.59
     whip
    -0.59
    POSITIVE LOGITS
    abilia
    1.00
     monument
    0.86
     nostalg
    0.86
     memorial
    0.85
     Statue
    0.85
     Revival
    0.83
     relic
    0.82
     honoring
    0.82
     cathedral
    0.81
     monuments
    0.81
    Activations Density 0.256%

    No Known Activations