© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18839
    Prev
    Next
    INDEX
    Explanations

    verbs related to time and actions that happen subsequently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "followed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.78
    ationally
    -0.67
    ãĥ³ãĤ¸
    -0.63
    iple
    -0.62
    rawling
    -0.60
    inen
    -0.60
    amount
    -0.59
    selves
    -0.59
    à©
    -0.55
    apest
    -0.55
    POSITIVE LOGITS
    .
    0.79
     thereafter
    0.75
    SPONSORED
    0.75
    ?
    0.73
    .[
    0.71
    .(
    0.70
    .*
    0.70
    .<
    0.70
     thereto
    0.70
     graduation
    0.70
    Activations Density 0.117%

    No Known Activations