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. 20842
    Prev
    Next
    INDEX
    Explanations

    references to individuals who have witnessed events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of witnesses in legal or testimonial 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
    Saharan
    -0.73
     McMaster
    -0.73
    ofi
    -0.71
    liga
    -0.70
    ooks
    -0.68
    osi
    -0.66
     Chop
    -0.66
    angu
    -0.64
    ogo
    -0.64
    corn
    -0.64
    POSITIVE LOGITS
     testimonies
    1.00
    Witness
    0.99
     testimony
    0.92
     witnesses
    0.90
     witness
    0.89
    ewitness
    0.89
     testify
    0.85
     Witnesses
    0.85
     testifying
    0.81
     Witness
    0.76
    Activations Density 0.016%

    No Known Activations