© 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. 11-RES-JB
    11. 9999
    Prev
    Next
    INDEX
    Explanations

    references to different modes of transportation, like boarding planes, boats, trains, and buses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to modes of transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roma
    -0.79
     openings
    -0.76
    parency
    -0.75
    ablishment
    -0.74
    Background
    -0.72
    criptions
    -0.71
     residue
    -0.68
     pores
    -0.68
    words
    -0.67
    AppData
    -0.67
    POSITIVE LOGITS
     plane
    1.43
     taxis
    1.37
     airplane
    1.36
     buses
    1.36
     helicopter
    1.36
     airliner
    1.33
     yacht
    1.30
     airplanes
    1.30
     boat
    1.28
     aircraft
    1.26
    Activations Density 0.362%

    No Known Activations