© 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. 1-RES-JB
    11. 3507
    Prev
    Next
    INDEX
    Explanations

    configurations or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to system configurations, particularly in relation to software and network setups

    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
    kids
    -0.75
    birth
    -0.74
    past
    -0.74
    child
    -0.71
    vest
    -0.70
    myra
    -0.69
    water
    -0.69
    ku
    -0.68
    conom
    -0.65
    inosaur
    -0.65
    POSITIVE LOGITS
     configurations
    1.37
     configuration
    1.24
    urations
    1.03
    eering
    1.02
     setups
    0.97
     configured
    0.96
    uration
    0.96
     Configuration
    0.95
     specifications
    0.90
    folios
    0.89
    Activations Density 0.008%

    No Known Activations