© 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. 6-RES-JB
    11. 7892
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Salt" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Salt Lake" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -1.09
    mercial
    -1.06
    ufact
    -0.93
     arrang
    -0.78
    enegger
    -0.76
     therap
    -0.74
    GROUP
    -0.68
    umper
    -0.66
    nces
    -0.66
     livest
    -0.66
    POSITIVE LOGITS
    zman
    1.06
    water
    1.01
    illo
    0.96
     Lake
    0.94
    Lake
    0.92
    ash
    0.89
    itude
    0.88
     Salt
    0.86
    ivas
    0.86
    bite
    0.84
    Activations Density 0.008%

    No Known Activations