© 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. 17186
    Prev
    Next
    INDEX
    Explanations

    references to physical locations or boundaries where movement occurs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crossing"

    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
    nesia
    -0.70
    wig
    -0.70
    ulously
    -0.66
    alus
    -0.65
    etic
    -0.63
    tml
    -0.63
    andum
    -0.63
     guiIcon
    -0.62
    Wan
    -0.62
    zip
    -0.62
    POSITIVE LOGITS
     crossings
    1.05
     crossing
    1.01
    roads
    0.94
    bows
    0.81
     Crossing
    0.78
     crosses
    0.77
    cross
    0.75
    engers
    0.74
    bow
    0.74
    es
    0.73
    Activations Density 0.009%

    No Known Activations