© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17067
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities taking place after a certain point in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "afterward" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ASE
    -0.69
    foot
    -0.68
    aez
    -0.66
    yu
    -0.64
    hma
    -0.63
    rod
    -0.63
    Especially
    -0.62
    vez
    -0.62
    eu
    -0.61
    ements
    -0.61
    POSITIVE LOGITS
     afterwards
    0.80
     afterward
    0.77
    aneously
    0.75
    etheless
    0.74
     disapp
    0.74
    EStream
    0.74
    noon
    0.74
     thereafter
    0.74
    rane
    0.71
    vernment
    0.69
    Activations Density 0.005%

    No Known Activations