© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12155
    Prev
    Next
    INDEX
    Explanations

    keywords related to software tools and functionalities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "View" and its variations indicating a user interface or display element

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     summons
    -0.71
     rhy
    -0.68
     canon
    -0.66
     anth
    -0.66
     racket
    -0.66
     hus
    -0.65
     bastard
    -0.65
     myself
    -0.64
     trump
    -0.62
     capital
    -0.62
    POSITIVE LOGITS
    View
    3.80
    view
    2.30
     View
    2.22
     Views
    1.91
     VIEW
    1.88
    VIEW
    1.80
    views
    1.78
     view
    1.69
     views
    1.42
    Story
    1.29
    Activations Density 0.013%

    No Known Activations