© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17152
    Prev
    Next
    INDEX
    Explanations

    mentions of medical procedures or anatomy, specifically related to mastectomy and mastodon

    oai_token-act-pair · gpt-3.5-turbo

    references to "mastodon" and "mastodon-related" topics

    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
    PsyNetMessage
    -0.78
    ITED
    -0.70
    çīĪ
    -0.69
    DragonMagazine
    -0.68
    Ô
    -0.68
     Physicians
    -0.67
    Madison
    -0.64
     Lauder
    -0.61
     GOODMAN
    -0.61
     Pepsi
    -0.61
    POSITIVE LOGITS
    odon
    1.08
     mast
    1.06
    mast
    1.03
    icated
    0.85
    ication
    0.81
    catentry
    0.78
    adish
    0.78
    iple
    0.76
    espie
    0.76
    iffs
    0.76
    Activations Density 0.017%

    No Known Activations