© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 18559
    Prev
    Next
    INDEX
    Explanations

    words related to tilting or leaning

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "tilt" in various contexts

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

    No Comments

    Negative Logits
    éĹĺ
    -0.76
    displayText
    -0.76
     Verd
    -0.70
    clamation
    -0.68
     Danger
    -0.68
    ãģķ
    -0.68
    Champ
    -0.68
    hazard
    -0.68
     è£ıç
    -0.68
    actionDate
    -0.67
    POSITIVE LOGITS
     tilt
    1.10
     tilted
    0.95
    ting
    0.95
    roid
    0.93
     til
    0.87
     toward
    0.81
    othy
    0.79
     towards
    0.75
     angle
    0.73
    terness
    0.72
    Activations Density 0.011%

    No Known Activations