© 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. 9-RES-JB
    11. 7203
    Prev
    Next
    INDEX
    Explanations

    phrases related to global political events and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government policies and regulations

    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
    ibaba
    -0.74
    bart
    -0.71
     glimps
    -0.70
    esta
    -0.66
    Reviewer
    -0.65
    lopp
    -0.64
     latent
    -0.62
     sophistication
    -0.59
    Interstitial
    -0.59
    andi
    -0.58
    POSITIVE LOGITS
     ASAP
    1.16
     indefinitely
    1.14
     lest
    1.00
     pending
    0.97
    instead
    0.96
     permanently
    0.92
     unilaterally
    0.90
     pursuant
    0.90
     citing
    0.90
     Instead
    0.89
    Activations Density 0.801%

    No Known Activations