© 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. 18571
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    personal reflections and experiences related to challenges and achievements

    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
    pires
    -0.80
     awaits
    -0.72
     manufactures
    -0.71
    erenn
    -0.69
     2022
    -0.68
     enterprise
    -0.68
     loudspe
    -0.66
     belongs
    -0.66
     enshr
    -0.65
     transact
    -0.65
    POSITIVE LOGITS
    Eventually
    1.16
     luckily
    1.11
    Luckily
    1.10
     hindsight
    1.10
     Thankfully
    1.08
    Thankfully
    1.05
    didn
    1.05
     Luckily
    1.05
     Eventually
    1.03
    felt
    1.00
    Activations Density 0.647%

    No Known Activations