© 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. 2-RES-JB
    11. 12554
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "agon"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "agon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.80
    bered
    -0.75
    putable
    -0.69
    bole
    -0.65
     CSI
    -0.62
    animate
    -0.62
     borrower
    -0.61
    FORMATION
    -0.61
    lished
    -0.60
    ynski
    -0.58
    POSITIVE LOGITS
    naire
    1.11
    xon
    0.98
    agon
    0.96
    naires
    0.90
    eus
    0.89
    otine
    0.86
    iola
    0.83
    insula
    0.80
    arium
    0.80
    zu
    0.78
    Activations Density 0.009%

    No Known Activations