© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific time points

    oai_token-act-pair · gpt-3.5-turbo

    the word "Since" followed by various numerical values or conditions

    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
    natureconservancy
    -0.75
     Pwr
    -0.64
     Defin
    -0.64
    dozen
    -0.63
    buster
    -0.62
    abor
    -0.61
    bart
    -0.61
    abul
    -0.61
    igans
    -0.61
    aber
    -0.60
    POSITIVE LOGITS
    rely
    1.90
     inception
    1.08
     2005
    1.03
     2006
    1.02
     1999
    1.00
     2002
    1.00
     2009
    0.99
     1976
    0.99
     1995
    0.98
     1992
    0.98
    Activations Density 0.049%

    No Known Activations