© 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. 1-RES-JB
    11. 11205
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a task as challenging or complex

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of challenging or complicated situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.79
    Interstitial
    -0.79
     Expend
    -0.77
    oration
    -0.75
    ood
    -0.73
    orters
    -0.72
    ulet
    -0.71
    ript
    -0.70
    VERTISEMENT
    -0.70
    ental
    -0.70
    POSITIVE LOGITS
     tricky
    1.34
    icult
    1.02
     undermin
    0.85
     pesky
    0.83
     forgiving
    0.82
     adolesc
    0.81
     delicate
    0.80
     challenging
    0.78
     difficult
    0.77
     navigating
    0.76
    Activations Density 0.004%

    No Known Activations