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. 11-RES-JB
    6. 8887
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events that happen after a certain point or occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an event or condition that occurs after a certain point in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.95
     guiActiveUn
    -0.73
    ãĤ¹
    -0.71
    ãĥī
    -0.65
     guiIcon
    -0.65
    女
    -0.64
    oho
    -0.64
    Ñĭ
    -0.63
    ãĥ¼
    -0.63
    ãĤ¹ãĥĪ
    -0.63
    POSITIVE LOGITS
     completing
    1.10
     sunset
    1.04
    noon
    1.03
     completion
    1.02
    market
    1.02
     midnight
    0.97
     subtract
    0.97
    though
    0.91
     exhausting
    0.91
    wards
    0.90
    Activations Density 0.085%

    No Known Activations