© 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. 4395
    Prev
    Next
    INDEX
    Explanations

    symbols or phrases related to Urdu language

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific name

    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
    SEC
    -0.60
     Leone
    -0.58
     McConnell
    -0.57
    weeney
    -0.56
    asers
    -0.56
    ptroller
    -0.56
     Cobra
    -0.55
    company
    -0.55
    FORE
    -0.55
    Xi
    -0.54
    POSITIVE LOGITS
    itives
    1.16
    erer
    1.11
    erers
    0.98
    s
    0.91
    itive
    0.86
    ened
    0.85
    eways
    0.83
    aby
    0.82
    ezvous
    0.81
    ish
    0.80
    Activations Density 0.031%

    No Known Activations