© 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. 11-RES-JB
    11. 14670
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical flipping or turning motions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flip" and its variations

    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
    lain
    -0.80
    ALLY
    -0.73
    ainment
    -0.69
     unfocusedRange
    -0.68
    urat
    -0.67
    ISE
    -0.66
    UGH
    -0.65
     Annotations
    -0.65
    ridor
    -0.64
    Definition
    -0.64
    POSITIVE LOGITS
     burgers
    1.06
     flo
    1.03
     flips
    0.91
    olitics
    0.91
    side
    0.87
     flipped
    0.85
    tera
    0.85
    fl
    0.85
     flip
    0.84
     flipping
    0.83
    Activations Density 0.039%

    No Known Activations