© 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. 12801
    Prev
    Next
    INDEX
    Explanations

    instances of the word "windows" combined with a number indicating the relevance or importance of the windows

    oai_token-act-pair · gpt-3.5-turbo

    references to windows, particularly in the context of damage or destruction

    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
    avez
    -0.85
    currency
    -0.75
    ghan
    -0.74
     Haram
    -0.71
     Flavoring
    -0.70
    icit
    -0.68
     recomm
    -0.66
    REDACTED
    -0.66
    oku
    -0.65
     PubMed
    -0.65
    POSITIVE LOGITS
     wip
    1.08
     pane
    0.97
     tint
    0.95
    glass
    0.93
     windows
    0.92
     sill
    0.91
    bars
    0.89
    door
    0.87
    ills
    0.85
    windows
    0.84
    Activations Density 0.020%

    No Known Activations