© 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 EvalsExportsinterp-engineNEWAPI 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. 20964
    Prev
    Next
    INDEX
    Explanations

    phrases with the term "so-called"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that criticize or reference the concept of "so-called" or perceived notions

    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
     attraction
    -0.79
     reservation
    -0.78
     TAMADRA
    -0.70
     Mock
    -0.68
     Mick
    -0.68
     reservations
    -0.66
     submission
    -0.63
     window
    -0.62
     Moff
    -0.61
     Inquiry
    -0.61
    POSITIVE LOGITS
    called
    1.91
    far
    1.24
    named
    1.20
    cial
    1.05
    much
    1.00
    often
    0.99
    described
    0.96
    many
    0.96
    bad
    0.92
    forth
    0.91
    Activations Density 0.016%

    No Known Activations