© 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. 11331
    Prev
    Next
    INDEX
    Explanations

    references to locations or people named "Pul"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or term, particularly "Pul," in varied contexts

    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
    ange
    -0.84
    gg
    -0.76
     GS
    -0.73
    finder
    -0.70
    nz
    -0.70
    rait
    -0.69
    artz
    -0.67
     egg
    -0.66
    aunt
    -0.65
    assetsadobe
    -0.65
    POSITIVE LOGITS
     Pul
    3.95
     pul
    1.98
     [+
    1.43
     Sul
    1.36
     pulp
    1.32
     Poc
    1.29
     Ply
    1.22
    ulp
    1.18
     Spur
    1.13
     Ful
    1.12
    Activations Density 0.041%

    No Known Activations