© 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. 10-RES-JB
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    the phrase "what kind of" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that categorize or describe types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.68
    arning
    -0.66
    ARY
    -0.62
    YR
    -0.61
    interstitial
    -0.60
    Ļ½
    -0.59
    umsy
    -0.59
     Beir
    -0.58
    VEL
    -0.56
    ģĸ
    -0.54
    POSITIVE LOGITS
     constitutes
    0.78
     havoc
    0.75
     qualifies
    0.74
     awaits
    0.72
    iles
    0.65
     tastes
    0.64
     interests
    0.63
    house
    0.63
    croft
    0.63
     happens
    0.62
    Activations Density 0.050%

    No Known Activations