© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8907
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis through the phrase "I mean"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or emphasis

    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
    "},"
    -0.69
    iership
    -0.67
    shaw
    -0.67
    -+-+
    -0.67
    onding
    -0.61
    bleacher
    -0.60
    ittered
    -0.60
    icum
    -0.60
    iets
    -0.60
    iated
    -0.59
    POSITIVE LOGITS
     yeah
    0.93
     REALLY
    0.88
     seriously
    0.86
     yea
    0.85
     honestly
    0.84
     LOOK
    0.77
     WHAT
    0.76
     hey
    0.76
     goodbye
    0.76
     listen
    0.75
    Activations Density 0.016%

    No Known Activations