© 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. 10-RES-JB
    11. 17477
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions involving grabbing or seizing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grab" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.83
    AMY
    -0.65
    enegger
    -0.64
    MQ
    -0.62
     Prol
    -0.60
     Reasons
    -0.60
    matter
    -0.60
    VERTISEMENT
    -0.60
    functional
    -0.60
     differe
    -0.60
    POSITIVE LOGITS
     hold
    1.21
     onto
    1.18
    hold
    1.10
    bage
    0.91
     grip
    0.90
    bing
    0.87
    bable
    0.86
     glances
    0.84
    bers
    0.83
     headlines
    0.80
    Activations Density 0.047%

    No Known Activations