© 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. 0-RES-JB
    11. 6513
    Prev
    Next
    INDEX
    Explanations

    sequences related to Raspberry Pi models

    oai_token-act-pair · gpt-3.5-turbo

    references to the Raspberry Pi computer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Saudi
    -0.96
     Saudi
    -0.81
     Saudis
    -0.69
     choked
    -0.68
    Enhanced
    -0.65
     trad
    -0.64
    ointed
    -0.63
     intox
    -0.62
     saturated
    -0.62
     Yemen
    -0.62
    POSITIVE LOGITS
     Pi
    3.89
    Pi
    3.19
     pi
    2.09
     Raspberry
    1.70
    pi
    1.67
     Pis
    1.67
     Phi
    1.49
     PI
    1.38
     Pie
    1.23
     Poles
    1.19
    Activations Density 0.014%

    No Known Activations