© 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. 1-RES-JB
    11. 3538
    Prev
    Next
    INDEX
    Explanations

    words related to the programming framework ASP

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.78
    house
    -0.75
    houses
    -0.75
     hazards
    -0.68
    hart
    -0.62
     Rove
    -0.62
    cers
    -0.61
     MacArthur
    -0.61
     Oval
    -0.60
     Hayward
    -0.60
    POSITIVE LOGITS
    asp
    1.51
    hemy
    1.13
    olicy
    0.89
    atchewan
    0.89
    retched
    0.89
    inator
    0.87
    asus
    0.84
    illary
    0.83
    ingu
    0.82
    alon
    0.80
    Activations Density 0.009%

    No Known Activations