© 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. 12573
    Prev
    Next
    INDEX
    Explanations

    references to specific universities and academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and associated numerical data

    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
    anwhile
    -0.29
    ardless
    -0.25
    quickShipAvailable
    -0.23
     timelines
    -0.23
     moreover
    -0.22
     meanwhile
    -0.22
     culminating
    -0.22
     thus
    -0.22
     dubbed
    -0.21
    staking
    -0.21
    POSITIVE LOGITS
    '),
    0.28
    idae
    0.26
    ")
    0.25
    "),
    0.25
    "))
    0.25
    /
    0.24
    "],
    0.23
    ')
    0.22
    ãĥ»
    0.22
     ):
    0.22
    Activations Density 2.687%

    No Known Activations