© 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. 11288
    Prev
    Next
    INDEX
    Explanations

    terms related to crossing or intersecting

    oai_token-act-pair · gpt-3.5-turbo

    the term "cross" in various 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
     Lav
    -0.73
    emonic
    -0.67
     Dur
    -0.66
     Barb
    -0.66
     phantom
    -0.66
     lav
    -0.65
     steady
    -0.63
     bat
    -0.63
     Emir
    -0.62
     Patty
    -0.62
    POSITIVE LOGITS
    cross
    4.51
    Cross
    1.92
    bred
    1.10
    fork
    1.10
    kiss
    1.07
     Crossing
    1.04
    brother
    1.01
    zee
    1.00
     crosses
    1.00
    travel
    0.99
    Activations Density 0.007%

    No Known Activations