© 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. 3-RES-JB
    11. 14805
    Prev
    Next
    INDEX
    Explanations

    phrases related to closures or shutting down

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shut," particularly in the context of closures or stoppages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Values
    -0.74
    ertodd
    -0.74
    omething
    -0.73
    ITNESS
    -0.69
    Fine
    -0.69
    Values
    -0.69
    URI
    -0.68
     Occupations
    -0.68
    minster
    -0.67
    Images
    -0.66
    POSITIVE LOGITS
    tered
    1.39
    tering
    1.20
    downs
    1.03
    tle
    0.98
    shut
    0.93
     shut
    0.93
    ters
    0.91
    down
    0.89
     sidel
    0.87
    lock
    0.86
    Activations Density 0.013%

    No Known Activations