© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 9216
    Prev
    Next
    INDEX
    Explanations

    words related to shipping and transportation, specifically focusing on parcel shipments

    oai_token-act-pair · gpt-3.5-turbo

    references to parcel shipments and cargo

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

    No Comments

    Negative Logits
    uli
    -0.77
    bered
    -0.76
    aldi
    -0.70
    ulton
    -0.68
    sle
    -0.68
    bern
    -0.67
    soft
    -0.66
    tan
    -0.66
    pmwiki
    -0.65
    nis
    -0.64
    POSITIVE LOGITS
     shipments
    1.18
     shipment
    1.09
     shipped
    0.82
    andise
    0.82
     crates
    0.80
     destined
    0.80
     merchandise
    0.79
     containers
    0.76
     cargo
    0.71
    loads
    0.71
    Activations Density 0.027%

    No Known Activations