Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3873
    Prev
    Next
    INDEX
    Explanations

    references to windows, especially when associated with various actions or descriptions like smashing, installing, or having certain characteristics like being small or tinted

    oai_token-act-pair · gpt-3.5-turbo

    references to windows in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.86
    currency
    -0.77
    ghan
    -0.74
    yss
    -0.69
     Flavoring
    -0.69
     Haram
    -0.68
    oku
    -0.67
     recomm
    -0.66
    Ô
    -0.66
     PubMed
    -0.66
    POSITIVE LOGITS
     wip
    1.05
     pane
    0.95
     sill
    0.93
    glass
    0.92
     tint
    0.91
     windows
    0.89
    door
    0.87
    bars
    0.87
     balcon
    0.84
    windows
    0.80
    Activations Density 0.014%

    No Known Activations