© 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. 20576
    Prev
    Next
    INDEX
    Explanations

    phrases related to depth or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deep"

    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
    perty
    -0.71
    cules
    -0.68
    annon
    -0.66
    uthor
    -0.65
    jee
    -0.65
    roma
    -0.65
    icans
    -0.64
     ATT
    -0.63
    hots
    -0.63
    alon
    -0.62
    POSITIVE LOGITS
    ened
    1.03
     vein
    0.94
     dive
    0.90
     breaths
    0.90
     pockets
    0.87
     dives
    0.87
     penetration
    0.85
    thro
    0.84
    ening
    0.82
     fry
    0.82
    Activations Density 0.034%

    No Known Activations