© 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. 1-RES-JB
    11. 3880
    Prev
    Next
    INDEX
    Explanations

    people or entities with names starting with "Th"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Th" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤŃ
    -0.90
    ãģĭ
    -0.88
    ITED
    -0.86
    ãģ®éŃĶ
    -0.86
    Spoiler
    -0.83
    ãĤ«
    -0.79
    ATION
    -0.79
    cloth
    -0.79
     Reloaded
    -0.78
    ATIONS
    -0.75
    POSITIVE LOGITS
    irteen
    1.07
    orne
    1.03
    reshold
    0.99
    umbnail
    0.98
    orns
    0.98
    irst
    0.94
    umb
    0.94
    izoph
    0.89
    orough
    0.87
    ought
    0.87
    Activations Density 0.006%

    No Known Activations