© 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. 2-RES-JB
    11. 3072
    Prev
    Next
    INDEX
    Explanations

    terms related to land occupation or farming, as well as words related to urinary tract infections and bacteria in the intestinal tract

    oai_token-act-pair · gpt-3.5-turbo

    references to land areas and farming equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.79
     largeDownload
    -0.76
    */(
    -0.70
    erd
    -0.64
    pires
    -0.63
    affer
    -0.62
     sober
    -0.62
     slideshow
    -0.61
    pload
    -0.59
    ccording
    -0.58
    POSITIVE LOGITS
     tracts
    1.29
     tract
    1.14
    ors
    1.01
    ttes
    0.88
    icular
    0.86
     Vaugh
    0.83
    eca
    0.82
    weed
    0.82
    oral
    0.82
     acre
    0.81
    Activations Density 0.008%

    No Known Activations