© 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. 11-RES-JB
    11. 20500
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a continuous or ongoing action or state

    oai_token-act-pair · gpt-3.5-turbo

    the word "ever" indicating ongoing situations or experiences

    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
    Reviewed
    -0.70
    aucus
    -0.69
    ouri
    -0.64
    esses
    -0.62
    animous
    -0.62
    Enlarge
    -0.62
    OUR
    -0.61
    icio
    -0.61
    our
    -0.60
    orst
    -0.60
    POSITIVE LOGITS
     since
    1.15
    thing
    1.09
    green
    1.02
    since
    0.98
    lasting
    0.86
    bilt
    0.86
    more
    0.85
     onward
    0.82
    last
    0.77
    theless
    0.76
    Activations Density 0.018%

    No Known Activations