© 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. 11-RES-JB
    11. 11383
    Prev
    Next
    INDEX
    Explanations

    actions and sequences of events in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "then" in conjunction with narratives or actions

    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
    utical
    -0.79
    itect
    -0.67
     Doctrine
    -0.63
    actionDate
    -0.61
    population
    -0.61
    haven
    -0.60
    Reviewer
    -0.60
     fruition
    -0.59
    limit
    -0.59
    soDeliveryDate
    -0.58
    POSITIVE LOGITS
     proceeded
    1.31
     walked
    1.26
     marched
    1.15
     climbed
    1.12
     drove
    1.08
     hugged
    1.07
     exited
    1.07
     headed
    1.05
     sped
    1.03
     resumed
    1.01
    Activations Density 0.169%

    No Known Activations