© 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. 11-RES-JB
    11. 20666
    Prev
    Next
    INDEX
    Explanations

    personal pronouns (I, we, you) and verbs related to action or observation

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal pronouns and references to individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olute
    -0.71
     Travels
    -0.67
    geoning
    -0.65
     Kard
    -0.64
    ardless
    -0.63
     Fill
    -0.60
     MFT
    -0.58
     Outbreak
    -0.58
     Prometheus
    -0.58
    ipient
    -0.56
    POSITIVE LOGITS
     disliked
    1.14
     dislike
    1.06
     learned
    0.98
     learnt
    0.96
     noticed
    0.96
     liked
    0.91
     hated
    0.91
     Learned
    0.88
     wished
    0.88
     overlooked
    0.86
    Activations Density 0.147%

    No Known Activations