© 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. 6-RES-JB
    11. 3541
    Prev
    Next
    INDEX
    Explanations

    words related to structures or objects found on the upper limits of enclosed spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to limitations or maximums, particularly related to ceilings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atri
    -0.80
    Ô
    -0.80
    ublic
    -0.78
    sylv
    -0.77
    uns
    -0.76
    atche
    -0.75
    uala
    -0.74
    ulf
    -0.73
    achu
    -0.71
    chev
    -0.69
    POSITIVE LOGITS
     ceilings
    1.30
     ceiling
    1.28
     heights
    0.94
     floor
    0.89
     rubble
    0.85
     carp
    0.84
     decoration
    0.84
     floors
    0.83
     pedest
    0.83
     decorations
    0.82
    Activations Density 0.012%

    No Known Activations