© 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. 10-RES-JB
    11. 13731
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific person or entity

    oai_token-act-pair · gpt-3.5-turbo

    words related to Irish culture and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avior
    -0.65
    anooga
    -0.65
     Archdemon
    -0.63
     BAD
    -0.59
     tragically
    -0.58
    arcity
    -0.57
     NCT
    -0.54
    rers
    -0.54
    creen
    -0.54
     Tycoon
    -0.54
    POSITIVE LOGITS
    isphere
    0.82
    versible
    0.76
    åĤ
    0.75
    ãĥij
    0.72
    icht
    0.70
    heim
    0.70
    INAL
    0.69
    Bir
    0.68
    gaard
    0.68
    ãĤ¤ãĥĪ
    0.67
    Activations Density 0.140%

    No Known Activations