© 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. 6-RES-JB
    11. 11883
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or person named "Middleton"

    oai_token-act-pair · gpt-3.5-turbo

    references to the town of Middle Town and its context within different narratives

    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
     metast
    -0.70
    pora
    -0.65
    economic
    -0.62
    lda
    -0.61
    TPP
    -0.60
    xon
    -0.59
     Nun
    -0.59
     convergence
    -0.58
     Canaver
    -0.57
    flu
    -0.56
    POSITIVE LOGITS
    itional
    0.99
    eenth
    0.99
    ety
    0.94
    ski
    0.94
    olph
    0.93
    elling
    0.90
    eret
    0.89
    ick
    0.88
    leground
    0.86
    olesc
    0.86
    Activations Density 0.016%

    No Known Activations