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

    Neuronpedia

    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. 10-RES-JB
    11. 12583
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering assistance or aid

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to assistance and support

    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
     preceded
    -0.72
     presided
    -0.67
    NetMessage
    -0.66
    llo
    -0.65
    payer
    -0.63
    \":
    -0.62
    mite
    -0.62
    ata
    -0.62
    ult
    -0.62
    levision
    -0.61
    POSITIVE LOGITS
     digestion
    0.99
     needy
    0.94
     grieving
    0.91
     cleanup
    0.85
     rebuilding
    0.85
     transition
    0.85
     recovery
    0.85
     recovering
    0.85
     distressed
    0.84
     reconstruction
    0.83
    Activations Density 0.178%

    No Known Activations