© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 604
    Prev
    Next
    INDEX
    Explanations

    phrases related to downplaying or detracting from the significance or impact of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "play" and its variations, indicating themes of performance or recreation

    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
     overcrowd
    -0.76
    Reviewer
    -0.72
     Bei
    -0.70
    idi
    -0.67
    «ĺ
    -0.64
     Fleet
    -0.62
    wcs
    -0.62
     prophetic
    -0.61
    zac
    -0.61
     millenn
    -0.61
    POSITIVE LOGITS
    halla
    0.93
    theless
    0.92
    plays
    0.92
    hyde
    0.87
    wright
    0.82
    ername
    0.81
    lihood
    0.79
    testers
    0.79
    station
    0.78
    GROUND
    0.76
    Activations Density 0.017%

    No Known Activations