© 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. 2-RES-JB
    11. 4487
    Prev
    Next
    INDEX
    Explanations

    references to vehicles and transportation, particularly "cruisers" and "destroyers."

    oai_token-act-pair · gpt-3.5-turbo

    references to naval vessels, specifically cruisers and destroyers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itives
    -0.84
    arov
    -0.80
    uries
    -0.74
    ura
    -0.73
    heny
    -0.72
    hens
    -0.72
    eas
    -0.72
    ologically
    -0.71
    aq
    -0.69
    estate
    -0.68
    POSITIVE LOGITS
     cruiser
    1.24
     Yamato
    0.89
    weight
    0.85
    alkyrie
    0.83
     USS
    0.81
     Cruiser
    0.80
    fish
    0.79
    ;;;;
    0.77
    ¯¯¯¯¯¯¯¯
    0.76
    maid
    0.76
    Activations Density 0.027%

    No Known Activations