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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9853
    Prev
    Next
    INDEX
    Explanations

    transition phrases signaling a continuation of a story or text content

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuation or ongoing narratives

    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
     ener
    -0.66
     feder
    -0.66
     federation
    -0.62
     bases
    -0.61
     toget
    -0.61
     reformed
    -0.61
     wisely
    -0.60
     reinvent
    -0.59
     reneg
    -0.59
    clud
    -0.58
    POSITIVE LOGITS
     Below
    1.05
     Transcript
    0.77
     Morning
    0.75
     Subscribe
    0.72
     CNBC
    0.67
    interstitial
    0.65
    govtrack
    0.65
     Previous
    0.64
     McCain
    0.64
     Reading
    0.63
    Activations Density 0.013%

    No Known Activations