© 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. 3-RES-JB
    11. 15205
    Prev
    Next
    INDEX
    Explanations

    references to the automotive brand "BMW"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific car brands, particularly BMW

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arters
    -0.80
    mond
    -0.73
    atro
    -0.72
    mary
    -0.66
    vere
    -0.66
    rencies
    -0.66
    pite
    -0.65
    laus
    -0.64
    peer
    -0.63
    oldemort
    -0.63
    POSITIVE LOGITS
     BMW
    0.84
     Motorsport
    0.80
    sonian
    0.73
     dealership
    0.72
     ank
    0.71
    bach
    0.69
    imil
    0.66
     sedan
    0.64
     radiator
    0.64
    ied
    0.63
    Activations Density 0.004%

    No Known Activations