© 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. 6-RES-JB
    11. 9534
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "inter" followed by a varying number, with some activations suggesting a pattern of decreasing values

    oai_token-act-pair · gpt-3.5-turbo

    references to interconnectivity or relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.73
    aimon
    -0.72
    ggle
    -0.72
    \/\/
    -0.67
    unks
    -0.65
    cffff
    -0.64
     Skydragon
    -0.64
    onna
    -0.64
    Magikarp
    -0.64
    ORK
    -0.63
    POSITIVE LOGITS
    mediate
    1.06
    ventions
    0.89
    vention
    0.85
    quart
    0.81
    views
    0.80
    active
    0.79
    pret
    0.77
    eering
    0.75
    actively
    0.74
    ing
    0.74
    Activations Density 0.011%

    No Known Activations