Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18005
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of arriving

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "arrive" and its variations, indicating discussions about arrival or coming to a place

    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
    tymology
    -0.79
    raid
    -0.78
    uyomi
    -0.77
    erenn
    -0.74
    addy
    -0.74
    ¥ŀ
    -0.73
    verbs
    -0.72
    frey
    -0.71
    oggle
    -0.71
    ietal
    -0.70
    POSITIVE LOGITS
     arrives
    0.82
     arrivals
    0.80
     Arri
    0.80
     arriving
    0.80
     arrive
    0.80
     WRITE
    0.78
     NX
    0.77
     Lank
    0.77
    Delivery
    0.76
     FedEx
    0.72
    Activations Density 0.011%

    No Known Activations