© 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. 0-RES-JB
    11. 12819
    Prev
    Next
    INDEX
    Explanations

    terms related to "tetraquark" or "pentaquark" states in particle physics

    oai_token-act-pair · gpt-3.5-turbo

    words related to rat behavior or references to rats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inert
    -0.68
     LG
    -0.64
     equivalents
    -0.64
     explanatory
    -0.63
     replacements
    -0.63
     flirt
    -0.62
     accounting
    -0.61
     discont
    -0.61
     inactive
    -0.61
     cig
    -0.60
    POSITIVE LOGITS
    ra
    4.11
    ras
    2.05
    RA
    1.92
    raf
    1.82
    rap
    1.78
    ran
    1.75
    rah
    1.73
    rab
    1.70
    raising
    1.58
    rak
    1.54
    Activations Density 0.023%

    No Known Activations