© 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. 10-RES-JB
    11. 20437
    Prev
    Next
    INDEX
    Explanations

    words related to challenges, difficulties, or struggles

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with attempts, difficulties, or struggles

    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
     Warning
    -0.71
    acted
    -0.69
    AAA
    -0.69
     Offensive
    -0.65
    hemy
    -0.65
     Concern
    -0.65
     Used
    -0.64
     forwarded
    -0.62
    laughter
    -0.62
    calling
    -0.61
    POSITIVE LOGITS
     survive
    1.43
     cope
    1.41
     regain
    1.23
     reconcile
    1.22
     maintain
    1.22
     fend
    1.20
     navigate
    1.18
     overcome
    1.17
     conceive
    1.15
     recover
    1.13
    Activations Density 0.159%

    No Known Activations