© 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. 20613
    Prev
    Next
    INDEX
    Explanations

    locations where events happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that specify locations or places in a narrative

    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
     incent
    -0.67
     Pwr
    -0.65
    TAG
    -0.64
    Grade
    -0.63
    âĨ
    -0.63
    apult
    -0.62
    TE
    -0.61
    izu
    -0.60
    idia
    -0.60
    greg
    -0.60
    POSITIVE LOGITS
    upon
    1.91
     they
    1.15
    soever
    1.09
     he
    1.03
     she
    0.91
     it
    0.87
    abouts
    0.81
     temperatures
    0.79
     many
    0.79
     we
    0.75
    Activations Density 0.055%

    No Known Activations