© 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. 2-RES-JB
    11. 15863
    Prev
    Next
    INDEX
    Explanations

    phrases containing the phrase "so-called"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "so-called"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORTS
    -0.70
    erves
    -0.67
     Restaur
    -0.67
     Column
    -0.63
    ositories
    -0.62
    YC
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.62
    alon
    -0.62
     Indies
    -0.61
    cean
    -0.61
    POSITIVE LOGITS
    called
    1.08
    call
    0.98
    calling
    0.87
    terday
    0.85
    uled
    0.82
    代
    0.80
     called
    0.79
    interstitial
    0.79
    selves
    0.78
    aires
    0.70
    Activations Density 0.016%

    No Known Activations