© 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. 1803
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are being referred to

    oai_token-act-pair · gpt-3.5-turbo

    references to something being "referred to."

    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
     depended
    -0.72
     dilig
    -0.65
     reliant
    -0.65
     relies
    -0.65
     brittle
    -0.64
     subsequ
    -0.64
    hop
    -0.64
     endeav
    -0.62
     appealed
    -0.62
     advoc
    -0.62
    POSITIVE LOGITS
    Ô
    0.85
    ãĤ´ãĥ³
    0.78
    èĢħ
    0.70
    ript
    0.69
    othy
    0.67
     Parables
    0.66
    ãĤ¯
    0.66
    PsyNetMessage
    0.65
    ãĤ¨ãĥ«
    0.65
    andise
    0.64
    Activations Density 0.164%

    No Known Activations