© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 22380
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuation or persistence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express continuity or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.80
    quickShipAvailable
    -0.73
    starting
    -0.66
    Sure
    -0.66
    anooga
    -0.65
    OTAL
    -0.65
    soDeliveryDate
    -0.64
     Binding
    -0.63
    MAT
    -0.61
    liest
    -0.61
    POSITIVE LOGITS
     operate
    1.07
     accumulate
    1.05
     refine
    1.03
     strive
    0.99
     pour
    0.98
     evolve
    0.98
     enjoy
    0.97
     rely
    0.97
     pursue
    0.96
     receive
    0.96
    Activations Density 0.056%

    No Known Activations