© 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. 854
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending with "GI"

    oai_token-act-pair · gpt-4-turbo

    acronyms or initialisms related to technology or organizations.

    oai_token-act-pair · gpt-3.5-turbo

    variations of the abbreviation "GI" as well as related terms and acronyms

    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
    manship
    -0.93
     Machina
    -0.79
    icity
    -0.77
    peak
    -0.75
    Merit
    -0.74
    ions
    -0.73
    supp
    -0.72
    words
    -0.70
     Debor
    -0.70
    drawn
    -0.70
    POSITIVE LOGITS
    GI
    1.10
    ogo
    1.03
    OSH
    1.01
    vernment
    0.97
    ORGE
    0.96
    RECT
    0.91
    OPA
    0.86
    OV
    0.85
    INT
    0.83
    ANT
    0.82
    Activations Density 0.011%

    No Known Activations