© 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. 0-RES-JB
    11. 8219
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "after."

    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
    represent
    -0.58
    SOURCE
    -0.56
    acus
    -0.56
    enza
    -0.56
    HCR
    -0.55
    Role
    -0.55
    tumblr
    -0.55
    Kin
    -0.54
    apest
    -0.53
    yip
    -0.53
    POSITIVE LOGITS
     after
    2.68
    after
    2.22
     afterward
    1.96
     afterwards
    1.95
     AFTER
    1.93
     thereafter
    1.56
     After
    1.54
    After
    1.54
     following
    1.49
     shortly
    1.41
    Activations Density 0.096%

    No Known Activations