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. 18264
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and events, specifically actions happening in the past or about to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of commas in sentences

    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
    ++;
    -0.69
    oubt
    -0.68
    rontal
    -0.66
    scribe
    -0.65
     Tycoon
    -0.65
    VERTISEMENT
    -0.64
    enf
    -0.64
    thora
    -0.63
    apest
    -0.63
    meric
    -0.62
    POSITIVE LOGITS
     issuing
    1.23
     posting
    1.22
     delivering
    1.21
     acquiring
    1.20
     registering
    1.20
     donating
    1.19
     deploying
    1.18
     launching
    1.18
     releasing
    1.18
     collecting
    1.17
    Activations Density 0.268%

    No Known Activations