© 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. 7441
    Prev
    Next
    INDEX
    Explanations

    information related to time, specifically events or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    the word 'the' in various contexts

    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
    <?
    -0.89
    ãĥĦ
    -0.74
    ply
    -0.73
    raised
    -0.72
     âĢº
    -0.72
    among
    -0.71
    ragon
    -0.68
    è¦
    -0.67
    Clar
    -0.67
    ãĤ¢ãĥ«
    -0.67
    POSITIVE LOGITS
     onset
    1.23
     arrival
    1.16
     deadline
    1.15
     expiration
    1.07
     advent
    1.06
     inevitable
    0.94
     commencement
    0.93
     fateful
    0.92
     inauguration
    0.92
     outbreak
    0.91
    Activations Density 0.101%

    No Known Activations