© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4584
    Prev
    Next
    INDEX
    Explanations

    words related to terraces

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words associated with fear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.71
     writ
    -0.67
     bacon
    -0.63
     modesty
    -0.62
     messenger
    -0.61
     plur
    -0.59
     Mub
    -0.59
     carrot
    -0.59
    --------------------------------------------------------
    -0.58
     surrogate
    -0.58
    POSITIVE LOGITS
    aces
    1.72
    aced
    1.60
    acing
    1.54
    ace
    1.42
    acer
    1.25
    ains
    1.24
    acements
    1.18
    acers
    1.14
    acement
    1.11
    asures
    1.05
    Activations Density 0.063%

    No Known Activations