© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    terms related to skyscrapers, space, and scaffolding

    oai_token-act-pair · gpt-3.5-turbo

    words related to skyscrapers and spatial concepts

    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
    BuyableInstoreAndOnline
    -0.86
     Pompe
    -0.71
     wholly
    -0.64
    ortium
    -0.64
    lander
    -0.63
    fman
    -0.63
    ument
    -0.63
    cise
    -0.62
    culosis
    -0.62
     Vlad
    -0.61
    POSITIVE LOGITS
    allows
    1.00
    reek
    0.82
    raper
    0.80
    ¥
    0.78
    immers
    0.78
     skysc
    0.77
    aped
    0.77
    Applications
    0.77
     ank
    0.76
    ILLE
    0.74
    Activations Density 0.025%

    No Known Activations