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

    Neuronpedia

    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. 9-RES-JB
    11. 5405
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift in focus or topic in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that stress the importance of time-related 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
    #$
    -0.68
    campus
    -0.64
    izes
    -0.63
    buster
    -0.63
    elight
    -0.63
    onet
    -0.61
     regretted
    -0.59
    Done
    -0.58
    hur
    -0.57
    opl
    -0.57
    POSITIVE LOGITS
     sake
    1.46
     purposes
    1.20
     meantime
    1.04
     foreseeable
    0.95
     longest
    0.94
     unin
    0.89
     moment
    0.87
     reasons
    0.87
     avoidance
    0.86
     instance
    0.82
    Activations Density 0.081%

    No Known Activations