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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 17652
    Prev
    Next
    INDEX
    Explanations

    references to a specific term or concept related to liberation or freedom

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the term "Liber" 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
    soDeliveryDate
    -0.78
    enegger
    -0.75
     à¨
    -0.70
    IELD
    -0.67
    BOOK
    -0.67
     Cth
    -0.66
    WAY
    -0.64
    OUT
    -0.63
    bone
    -0.62
     deaf
    -0.61
    POSITIVE LOGITS
    tarians
    1.41
    tarian
    1.11
    ator
    1.02
    itas
    1.01
    ated
    1.00
    iously
    0.99
    ations
    0.96
    gence
    0.95
    ators
    0.95
    ately
    0.94
    Activations Density 0.012%

    No Known Activations