© 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. 13561
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific locations, specifically "Ches(sire)"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and places

    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
    ãĥ³ãĤ¸
    -0.92
     depreciation
    -0.69
    osit
    -0.64
    estation
    -0.63
    duct
    -0.60
     traffic
    -0.57
    IUM
    -0.56
    endar
    -0.56
     variance
    -0.55
    ibraries
    -0.55
    POSITIVE LOGITS
    apeake
    0.98
    hire
    0.85
    soDeliveryDate
    0.79
    nces
    0.77
    enegger
    0.75
     Ples
    0.75
    peria
    0.74
    hops
    0.74
    pine
    0.73
    borough
    0.73
    Activations Density 0.058%

    No Known Activations