© 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. 7784
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting or delineating points

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that emphasize contrasts or contradictions

    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
    iffe
    -0.67
    eni
    -0.67
    IER
    -0.65
    VIS
    -0.64
     Became
    -0.62
    hurst
    -0.61
    aky
    -0.61
    USS
    -0.60
    RESULTS
    -0.60
    uman
    -0.59
    POSITIVE LOGITS
     nor
    1.78
    nor
    1.38
     anymore
    1.09
     Nor
    1.05
    although
    1.02
     but
    1.02
     though
    0.97
     Rather
    0.96
     although
    0.95
     merely
    0.94
    Activations Density 0.147%

    No Known Activations