© 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. 7-RES-JB
    11. 23903
    Prev
    Next
    INDEX
    Explanations

    references to the extent or scale of various situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to the scale or magnitude of issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.92
    advertising
    -0.80
    é¾įå
    -0.79
    uay
    -0.75
    ants
    -0.73
    wait
    -0.72
    nis
    -0.72
    enium
    -0.71
    addin
    -0.71
    center
    -0.69
    POSITIVE LOGITS
     devastation
    0.92
     coverage
    0.88
     threat
    0.86
     hostilities
    0.85
     penetration
    0.85
     damage
    0.84
     disparity
    0.83
     significance
    0.80
     difference
    0.80
     indebted
    0.78
    Activations Density 0.131%

    No Known Activations