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. 0-RES-JB
    6. 21121
    Prev
    Next
    INDEX
    Explanations

    phrases related to bodily issues

    oai_token-act-pair · gpt-3.5-turbo

    references to bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Torrent
    -0.66
     Wik
    -0.63
     Yahoo
    -0.63
    oway
    -0.63
     eBay
    -0.62
    awei
    -0.62
    ahoo
    -0.60
     Fam
    -0.60
     households
    -0.59
    idas
    -0.59
    POSITIVE LOGITS
    ory
    1.22
    ories
    0.86
    vered
    0.74
    ORY
    0.71
    ãĤ¦ãĤ¹
    0.70
    QUIRE
    0.70
    oire
    0.69
    anim
    0.69
    heimer
    0.68
    ODY
    0.67
    Activations Density 0.001%

    No Known Activations