© 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. 2-RES-JB
    11. 12751
    Prev
    Next
    INDEX
    Explanations

    locations or names with the term "Los" or "Lone"

    oai_token-act-pair · gpt-3.5-turbo

    references to Los Angeles and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ternity
    -0.74
     backdrop
    -0.68
    riad
    -0.66
    ree
    -0.66
     miscarriage
    -0.63
     tremend
    -0.63
    framework
    -0.62
     chance
    -0.62
    unn
    -0.62
     Seym
    -0.61
    POSITIVE LOGITS
     Angeles
    0.92
    boa
    0.87
    cano
    0.84
    LOS
    0.84
     ANGEL
    0.83
    opsis
    0.81
    aurus
    0.79
    HUD
    0.77
    otomy
    0.77
    utenant
    0.74
    Activations Density 0.005%

    No Known Activations