© 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. 3-RES-JB
    11. 23580
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Dart" or "Dartmouth"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Dart" along with references to hair dyeing and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.71
    uilt
    -0.69
    helle
    -0.69
    Magikarp
    -0.67
    olulu
    -0.67
    yrim
    -0.67
    orthern
    -0.66
    »Ĵ
    -0.66
    undai
    -0.65
     tradem
    -0.64
    POSITIVE LOGITS
     dart
    1.01
     darts
    1.00
     Swim
    0.85
    enegger
    0.82
    zeb
    0.81
    agher
    0.81
    board
    0.80
     Dart
    0.77
    nell
    0.77
    schild
    0.74
    Activations Density 0.012%

    No Known Activations