© 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. 2-RES-JB
    11. 3118
    Prev
    Next
    INDEX
    Explanations

    phrases pointing out the importance of various things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significance or importance in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á
    -0.87
    IDES
    -0.80
    AUT
    -0.78
    bows
    -0.77
    thus
    -0.77
    ilk
    -0.75
    default
    -0.72
    Bow
    -0.72
    thur
    -0.72
    ILA
    -0.71
    POSITIVE LOGITS
     proble
    0.87
     contributors
    0.86
     distingu
    0.85
     decisions
    0.81
    allery
    0.80
     importance
    0.77
     important
    0.76
     contributor
    0.76
     portions
    0.75
     distinction
    0.75
    Activations Density 0.030%

    No Known Activations