© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    initials 'PA' with a number following it

    oai_token-act-pair · gpt-3.5-turbo

    references to 'PA', likely indicating mentions of Pennsylvania or a related topic

    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
    naire
    -0.87
    lings
    -0.83
    worms
    -0.77
    lasses
    -0.68
    enegger
    -0.68
    ãĤ¦
    -0.68
    minded
    -0.67
    tie
    -0.67
    aries
    -0.67
    link
    -0.66
    POSITIVE LOGITS
    PA
    1.01
    UL
    1.01
    WN
    0.96
     PA
    0.92
    IRED
    0.91
    itone
    0.89
    EA
    0.85
    insula
    0.81
    BR
    0.79
    WAY
    0.79
    Activations Density 0.004%

    No Known Activations