© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce a subject or discuss ownership

    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
    170
    -0.72
    0002
    -0.69
    leaf
    -0.69
     Checking
    -0.68
    USA
    -0.68
    ³³³³
    -0.68
     Mayo
    -0.67
    PL
    -0.66
    Ven
    -0.65
    PRESS
    -0.65
    POSITIVE LOGITS
    soever
    1.10
     ancestors
    0.91
     sole
    0.87
     own
    0.84
     transports
    0.83
     courage
    0.75
     fault
    0.75
    ibling
    0.73
     cares
    0.72
     accompanies
    0.72
    Activations Density 0.014%

    No Known Activations