© 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. 4-RES-JB
    11. 10675
    Prev
    Next
    INDEX
    Explanations

    people who are observers or watch things happening

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "observer."

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

    No Comments

    Negative Logits
    eways
    -0.72
    Ingredients
    -0.69
    illard
    -0.67
    Hom
    -0.66
    Enough
    -0.66
    Tax
    -0.64
    Interstitial
    -0.63
    eating
    -0.63
    GET
    -0.61
    ten
    -0.61
    POSITIVE LOGITS
     observer
    1.22
     observers
    1.19
     wat
    0.95
     observing
    0.84
    acers
    0.82
    auts
    0.77
    opol
    0.77
     blinded
    0.75
    obook
    0.74
    etheless
    0.72
    Activations Density 0.015%

    No Known Activations