© 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. 9312
    Prev
    Next
    INDEX
    Explanations

    words or acronyms related to the company "GE" (General Electric)

    oai_token-act-pair · gpt-3.5-turbo

    references to General Electric (GE) in various contexts

    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
    olulu
    -0.84
    ties
    -0.75
    iqueness
    -0.73
    skilled
    -0.72
    supp
    -0.72
    gettable
    -0.71
    kefeller
    -0.71
    oola
    -0.70
     Dragonbound
    -0.69
    icum
    -0.68
    POSITIVE LOGITS
    ORGE
    1.24
    hog
    0.97
    orge
    0.93
    ASE
    0.92
    ARCH
    0.89
    ONT
    0.83
    ICO
    0.81
    PS
    0.79
    GEN
    0.79
    ASY
    0.78
    Activations Density 0.006%

    No Known Activations