© 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. 9-RES-JB
    11. 2367
    Prev
    Next
    INDEX
    Explanations

    terms with the phrase "so-called"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "so-called" used to refer to groups or categories in a critical 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
    erves
    -0.70
     furthermore
    -0.70
     nevertheless
    -0.68
    ande
    -0.64
    ttes
    -0.64
    rehens
    -0.63
     nonetheless
    -0.63
    _-
    -0.63
     moreover
    -0.63
    ORTS
    -0.62
    POSITIVE LOGITS
     "#
    0.94
     "
    0.90
    metadata
    0.83
     caliphate
    0.82
    judicial
    0.79
     Islamic
    0.75
     '
    0.75
    ordinary
    0.73
    advant
    0.72
    social
    0.72
    Activations Density 0.046%

    No Known Activations