© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    phrases related to imbalance or bias in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of balance or swinging between opposing forces

    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
     Paste
    -0.78
    asking
    -0.70
    ciating
    -0.67
    ufact
    -0.66
    hid
    -0.66
    CRIP
    -0.65
     typo
    -0.64
    itary
    -0.63
    BUR
    -0.62
     proclamation
    -0.61
    POSITIVE LOGITS
     favour
    1.33
     toward
    1.29
     towards
    1.26
     favor
    1.24
    oward
    1.19
     favoring
    1.16
     downwards
    1.05
     Favor
    1.05
     downward
    1.03
     decisively
    1.02
    Activations Density 0.235%

    No Known Activations