© 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. 666
    Prev
    Next
    INDEX
    Explanations

    references to physical structures above a certain level

    oai_token-act-pair · gpt-3.5-turbo

    references to ceilings or upper limits

    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
    Ô
    -0.80
    uns
    -0.75
    amide
    -0.73
    atri
    -0.73
    xy
    -0.70
    nie
    -0.69
    fortune
    -0.69
    ãģ®éŃĶ
    -0.69
    Southern
    -0.68
    achu
    -0.68
    POSITIVE LOGITS
     ceiling
    1.46
     ceilings
    1.45
     floor
    0.96
     pedest
    0.87
     Floor
    0.87
     floors
    0.86
     curtains
    0.84
     mural
    0.84
     heights
    0.83
     decoration
    0.82
    Activations Density 0.004%

    No Known Activations