© 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. 0-RES-JB
    6. 14770
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something arrives at a location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "arrived"

    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
    hibition
    -0.61
     cess
    -0.61
    hib
    -0.60
     Vice
    -0.58
     Prohibition
    -0.58
    vp
    -0.56
     Perkins
    -0.56
    ript
    -0.56
     Unreal
    -0.55
    laughs
    -0.55
    POSITIVE LOGITS
     arrived
    3.48
     arrives
    2.45
     arrive
    2.41
     arriving
    1.91
     arrival
    1.68
     landed
    1.47
     entered
    1.47
     sailed
    1.46
     Arri
    1.44
     departed
    1.43
    Activations Density 0.014%

    No Known Activations