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. 24230
    Prev
    Next
    INDEX
    Explanations

    instances of people coming forward with information or accusations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come forward."

    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
    tein
    -0.79
    rip
    -0.76
     Bots
    -0.64
    ľ
    -0.63
    icion
    -0.63
    Rocket
    -0.62
    OME
    -0.62
     Moj
    -0.60
    OL
    -0.60
    acca
    -0.59
    POSITIVE LOGITS
     testimonies
    0.76
     voluntarily
    0.76
     allegations
    0.75
     toile
    0.70
    comings
    0.70
    wcs
    0.68
    osal
    0.68
    circle
    0.66
     accusations
    0.66
     submissions
    0.61
    Activations Density 0.013%

    No Known Activations