© 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 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. 2-RES-JB
    11. 8924
    Prev
    Next
    INDEX
    Explanations

    terms related to problem-solving and actions taken to resolve various issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to addressing issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akin
    -0.73
    ischer
    -0.68
     Fav
    -0.67
    axis
    -0.67
     Mehran
    -0.66
    ooks
    -0.64
     Bees
    -0.63
     fiction
    -0.63
    umbers
    -0.62
    apt
    -0.62
    POSITIVE LOGITS
     address
    0.98
     addresses
    0.93
     Address
    0.89
    address
    0.89
    Address
    0.84
     addressing
    0.77
     addr
    0.71
    ãĤ©
    0.71
    velt
    0.70
    ãĤ¼ãĤ¦ãĤ¹
    0.70
    Activations Density 0.014%

    No Known Activations