© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 3398
    Prev
    Next
    INDEX
    Explanations

    references to packages being picked up, delivered, or dealing with software or insurance packages

    oai_token-act-pair · gpt-3.5-turbo

    references to packages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.74
    SOURCE
    -0.72
    BN
    -0.71
    Commission
    -0.70
    Ba
    -0.69
     Democrat
    -0.69
    Hz
    -0.68
    BF
    -0.68
     Greens
    -0.68
     Democratic
    -0.67
    POSITIVE LOGITS
     packages
    1.34
    uggest
    1.22
    ometimes
    1.04
    mith
    1.03
    poons
    1.03
    avorite
    1.01
    hops
    1.01
    htaking
    1.00
    packages
    0.98
    etting
    0.97
    Activations Density 0.011%

    No Known Activations