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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4620
    Prev
    Next
    INDEX
    Explanations

    specific types of media sources or channels

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets

    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
    itous
    -0.67
     married
    -0.64
    arse
    -0.64
     Solitaire
    -0.63
     mathematical
    -0.62
     DES
    -0.62
     CGI
    -0.62
     Modified
    -0.62
    mar
    -0.61
    doc
    -0.60
    POSITIVE LOGITS
     outlets
    3.64
     outlet
    3.17
     channels
    1.39
     venues
    1.26
     distributors
    1.22
     sources
    1.21
     publications
    1.20
     stations
    1.17
     establishments
    1.15
     stores
    1.14
    Activations Density 0.029%

    No Known Activations