© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21468
    Prev
    Next
    INDEX
    Explanations

    phrases related to being challenged or facing difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to facing or being confronted with challenges or conflicts

    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
    iew
    -0.67
    entry
    -0.62
     Awards
    -0.61
     exempted
    -0.56
    ools
    -0.56
    amina
    -0.55
     toast
    -0.55
     exports
    -0.54
     beneficiary
    -0.54
     fertilizer
    -0.53
    POSITIVE LOGITS
    ational
    0.91
     dile
    0.83
     adversity
    0.83
     confront
    0.81
     confronted
    0.81
     confronts
    0.81
     confronting
    0.80
     faced
    0.80
    chall
    0.79
     squarely
    0.78
    Activations Density 0.052%

    No Known Activations