© 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. 9-RES-JB
    11. 22961
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles, challenges or difficulties

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orf
    -0.76
    eah
    -0.74
    olphins
    -0.73
    sburg
    -0.73
    daq
    -0.72
    ream
    -0.71
    ivery
    -0.70
    mberg
    -0.70
    psc
    -0.69
    ergy
    -0.67
    POSITIVE LOGITS
     barriers
    1.03
     erected
    0.99
     obstacles
    0.97
     preventing
    0.97
     obstacle
    0.96
     impede
    0.89
     blocking
    0.88
     barrier
    0.87
     hurdles
    0.83
     insur
    0.83
    Activations Density 0.055%

    No Known Activations