© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17392
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "PI" associated with data points or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "PI" and related concepts

    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
    suit
    -1.03
    spread
    -0.94
    sound
    -0.85
    sword
    -0.82
    suits
    -0.80
    space
    -0.80
    birds
    -0.79
    speed
    -0.78
    nell
    -0.78
    pool
    -0.77
    POSITIVE LOGITS
    PI
    1.06
    KA
    0.93
    ZZ
    0.92
    OGR
    0.89
    PS
    0.84
    HK
    0.80
    KK
    0.80
    ropri
    0.77
    PLA
    0.77
    YA
    0.77
    Activations Density 0.008%

    No Known Activations