© 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. 9-RES-JB
    11. 3499
    Prev
    Next
    INDEX
    Explanations

    keywords related to concepts and topics within a specific domain or category

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sections that discuss associations or connections to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.82
    imates
    -0.76
    âķIJ
    -0.76
    NER
    -0.71
    ellen
    -0.71
    onew
    -0.70
    ifter
    -0.69
    ypes
    -0.69
    matched
    -0.68
    uckland
    -0.67
    POSITIVE LOGITS
     thereto
    1.13
     mater
    0.83
    worldly
    0.81
    ness
    0.80
    matter
    0.79
     topics
    0.77
     matters
    0.76
     closely
    0.73
     unrelated
    0.72
     ancest
    0.70
    Activations Density 0.045%

    No Known Activations