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. 7148
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Hugh Hewitt."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in a conversational or interview context

    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
    CLASSIFIED
    -0.72
    ģ«
    -0.70
     surve
    -0.70
    ĸļ
    -0.68
     circulation
    -0.67
    ifully
    -0.66
     brill
    -0.65
     recoil
    -0.65
     locking
    -0.65
     confir
    -0.65
    POSITIVE LOGITS
    pter
    1.04
    esy
    0.93
    neys
    0.91
    stall
    0.85
    oenix
    0.80
    Ö¼
    0.79
    ati
    0.78
    dos
    0.78
    pot
    0.75
    mong
    0.72
    Activations Density 0.045%

    No Known Activations