© 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. 3-RES-JB
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    instances where the word "only" appears with a high activation value indicating emphasis or exclusivity

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" and its variations highlighting exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.80
    idon
    -0.73
    finder
    -0.70
    arted
    -0.63
     Dru
    -0.61
     heterogeneity
    -0.60
    actionDate
    -0.58
    Nev
    -0.56
    gnu
    -0.56
     Dill
    -0.56
    POSITIVE LOGITS
     marginally
    1.00
     incidentally
    0.82
    isons
    0.74
    onso
    0.73
     mildly
    0.69
     sparing
    0.69
     limited
    0.68
    ices
    0.68
     omit
    0.65
     valid
    0.65
    Activations Density 0.085%

    No Known Activations