© 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. 10-RES-JB
    11. 7232
    Prev
    Next
    INDEX
    Explanations

    phrases related to transportation and shipping

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of transportation and items being carried

    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
    aces
    -0.81
     pores
    -0.74
    acci
    -0.71
    loo
    -0.67
    â
    -0.67
     Appearance
    -0.67
    leon
    -0.65
    ydia
    -0.64
     brow
    -0.64
    ħĭ
    -0.63
    POSITIVE LOGITS
     passengers
    1.35
     cargo
    1.34
     goods
    1.24
     migrants
    1.18
     supplies
    1.13
     payload
    1.07
     pilgrims
    1.02
     refugees
    1.01
     belongings
    0.99
     luggage
    0.99
    Activations Density 0.294%

    No Known Activations