© 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. 3-RES-JB
    11. 23413
    Prev
    Next
    INDEX
    Explanations

    references to 360-degree content or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "360," particularly in contexts related to video technology or gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nell
    -0.94
    minist
    -0.79
    ems
    -0.77
    prises
    -0.72
    itism
    -0.71
    ãĤ°
    -0.70
    geist
    -0.69
    nie
    -0.69
    alg
    -0.68
    taining
    -0.67
    POSITIVE LOGITS
    °
    1.12
     degrees
    0.96
     360
    0.87
    º
    0.87
     Deg
    0.82
     Degree
    0.77
    deg
    0.73
    360
    0.71
     ILCS
    0.71
     deg
    0.68
    Activations Density 0.013%

    No Known Activations