© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location named "Port"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Port" and its variations

    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
    soever
    -0.81
    IGHTS
    -0.75
    pta
    -0.68
     toget
    -0.65
    hower
    -0.64
    OWS
    -0.64
    IGH
    -0.62
     trailing
    -0.60
    KER
    -0.59
    kson
    -0.59
    POSITIVE LOGITS
    folio
    1.66
    folios
    1.56
    rait
    1.54
    raits
    1.49
    ugal
    1.31
    eur
    1.00
    ray
    0.98
    ugu
    0.96
     Canaveral
    0.91
     Adelaide
    0.87
    Activations Density 0.035%

    No Known Activations