© 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. 23921
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that indicate similarity or analogy

    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
    Published
    -0.72
     Semin
    -0.70
    ARDS
    -0.69
    ARD
    -0.69
     Sunshine
    -0.66
     Dresden
    -0.65
    士
    -0.65
    Delivery
    -0.63
    tan
    -0.63
    Forest
    -0.63
    POSITIVE LOGITS
    lihood
    1.25
     akin
    1.09
    etheless
    1.00
    entimes
    0.95
    awei
    0.89
     minded
    0.87
    minded
    0.87
    mares
    0.85
    interstitial
    0.80
    MpServer
    0.80
    Activations Density 0.006%

    No Known Activations