© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21756
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "agon" which can refer to struggle or contest

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitions or contests

    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
    ©¶æ
    -0.67
    FORMATION
    -0.66
    İĭ
    -0.62
    bered
    -0.60
     CSI
    -0.60
     borrower
    -0.59
     suggestive
    -0.59
    said
    -0.57
    ħĭ
    -0.55
     backlog
    -0.55
    POSITIVE LOGITS
    agon
    1.18
    naire
    0.96
    insula
    0.91
    xon
    0.90
    otine
    0.87
    cia
    0.87
    iola
    0.85
    ansas
    0.82
    istar
    0.81
    illin
    0.79
    Activations Density 0.006%

    No Known Activations