© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    words related to challenges, difficulties, hardships, and struggles

    oai_token-act-pair · gpt-3.5-turbo

    themes related to personal and emotional challenges

    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
    ongyang
    -0.86
    nesty
    -0.85
    asus
    -0.76
    tarian
    -0.73
    sheet
    -0.73
    rity
    -0.72
    itatively
    -0.70
    license
    -0.69
    exempt
    -0.69
    tarians
    -0.69
    POSITIVE LOGITS
     endured
    1.13
     inflicted
    1.05
     coping
    0.97
     overcame
    0.96
     overcome
    0.94
     encountered
    0.93
     plag
    0.93
     compounded
    0.91
     stemming
    0.91
     Inher
    0.90
    Activations Density 0.267%

    No Known Activations