© 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. 9-RES-JB
    11. 23944
    Prev
    Next
    INDEX
    Explanations

    verb phrases indicating progression or continuation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progression or actions taken in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.75
    eyes
    -0.73
     Continued
    -0.70
    enforcement
    -0.66
    Limited
    -0.65
    DOWN
    -0.65
    ese
    -0.64
     Context
    -0.64
    bub
    -0.64
    Edited
    -0.64
    POSITIVE LOGITS
     become
    1.11
     achieve
    1.08
     create
    1.06
     explore
    1.05
     develop
    1.05
     formulate
    1.05
     establish
    1.04
     discover
    1.03
     dismantle
    1.02
     earn
    1.01
    Activations Density 0.065%

    No Known Activations