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. 18768
    Prev
    Next
    INDEX
    Explanations

    conditional statements indicating hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expressions of hypothetical situations

    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
    rian
    -0.64
    atl
    -0.63
     languages
    -0.63
     Tayyip
    -0.61
    vable
    -0.61
    vered
    -0.60
    kay
    -0.60
     Pearce
    -0.60
    ving
    -0.59
    UFF
    -0.57
    POSITIVE LOGITS
    azo
    0.88
    DragonMagazine
    0.73
    rection
    0.72
     nevertheless
    0.68
    MpServer
    0.66
     goto
    0.65
     surely
    0.65
    DIV
    0.63
    Apps
    0.62
    '>
    0.62
    Activations Density 0.513%

    No Known Activations