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. 4-RES-JB
    6. 320
    Prev
    Next
    INDEX
    Explanations

    sentences where the word "show" is used in a commanding or directive context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "show."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.75
    ascus
    -0.68
     retaining
    -0.65
    retch
    -0.65
    undai
    -0.65
     batted
    -0.64
    leans
    -0.64
     inhabited
    -0.64
    tymology
    -0.63
     compounded
    -0.63
    POSITIVE LOGITS
    biz
    1.08
    runners
    0.98
    manship
    0.96
    alter
    0.95
    ered
    0.94
    runner
    0.85
    shows
    0.80
     Thumbnails
    0.75
    girls
    0.75
    downs
    0.74
    Activations Density 0.061%

    No Known Activations