© 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. 16591
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating dependency or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate dependency or conditionality

    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
    cknow
    -0.89
    BSD
    -0.86
    jah
    -0.79
    eas
    -0.76
    ãĥĨ
    -0.75
    kee
    -0.75
    ©¶æ¥µ
    -0.72
    together
    -0.72
    audi
    -0.70
    lyn
    -0.68
    POSITIVE LOGITS
     how
    1.28
     whether
    1.21
     circumstances
    1.17
     circumstance
    1.14
     factors
    0.95
     what
    0.94
     severity
    0.90
     timing
    0.88
     specifics
    0.84
     your
    0.84
    Activations Density 0.060%

    No Known Activations