© 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. 7-RES-JB
    11. 24085
    Prev
    Next
    INDEX
    Explanations

    words related to overcoming obstacles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overcome" and its variations in various contexts of challenge and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cas
    -0.92
    dar
    -0.78
    nesty
    -0.77
    abet
    -0.74
    colo
    -0.72
    pring
    -0.72
    overe
    -0.70
    Choice
    -0.69
    exempt
    -0.69
    othy
    -0.69
    POSITIVE LOGITS
     adversity
    1.10
     obstacles
    1.06
     hurdles
    0.95
     difficulties
    0.89
     hurdle
    0.88
     challenges
    0.86
     hardships
    0.86
     insur
    0.79
     setbacks
    0.79
     misconceptions
    0.79
    Activations Density 0.037%

    No Known Activations