© 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. 2-RES-JB
    11. 6951
    Prev
    Next
    INDEX
    Explanations

    URLs or terms related to website visits

    oai_token-act-pair · gpt-3.5-turbo

    references to visibility or the concept of something being visible

    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
    ¶ħ
    -0.77
     fractions
    -0.67
    riad
    -0.66
     piling
    -0.64
     Carnegie
    -0.63
    Ĥª
    -0.63
     doomed
    -0.62
     crust
    -0.61
     mammoth
    -0.61
     unfor
    -0.61
    POSITIVE LOGITS
    ibility
    1.35
    itors
    1.12
    ibly
    1.09
    vis
    1.07
    itor
    1.00
    ited
    0.98
    ision
    0.91
    ibl
    0.90
    apore
    0.88
    itation
    0.88
    Activations Density 0.012%

    No Known Activations