© 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. 8-RES-JB
    11. 7199
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals serving in different capacities or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "serve" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     converter
    -0.70
    razil
    -0.63
    ologists
    -0.62
    iques
    -0.61
    apest
    -0.61
    Ĥİ
    -0.61
    pex
    -0.60
    vu
    -0.60
    ophe
    -0.59
    sts
    -0.59
    POSITIVE LOGITS
    HTTP
    0.75
     horm
    0.74
    iments
    0.71
     faithfully
    0.69
    ences
    0.69
    lyak
    0.69
     alongside
    0.68
    entials
    0.68
    imony
    0.67
    fully
    0.67
    Activations Density 0.031%

    No Known Activations