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. 18486
    Prev
    Next
    INDEX
    Explanations

    words related to physical descriptions like "hunched," "huddled," "hanger," "blushing," etc

    oai_token-act-pair · gpt-3.5-turbo

    words related to breathing or physical exertion

    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
    BILITIES
    -0.94
    tions
    -0.82
    CHA
    -0.77
    BILITY
    -0.75
    taboola
    -0.71
     Iw
    -0.70
    oÄŁ
    -0.68
    Cause
    -0.68
     Cosponsors
    -0.67
     Sorce
    -0.65
    POSITIVE LOGITS
    angs
    0.80
    inki
    0.80
    ftime
    0.77
    awei
    0.76
    icultural
    0.74
    abee
    0.73
    agonal
    0.71
     flock
    0.70
    iday
    0.70
    acan
    0.70
    Activations Density 0.075%

    No Known Activations