© 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. 24353
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of fiber optics and related technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to fiber or fibre, particularly in relation to telecommunications or structural materials

    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
    oice
    -0.75
    eton
    -0.74
    ean
    -0.74
     Standing
    -0.66
    ammad
    -0.66
    aurus
    -0.66
    isters
    -0.64
    hare
    -0.63
     Mehran
    -0.63
    inav
    -0.62
    POSITIVE LOGITS
     optic
    1.41
    glass
    1.29
    glas
    1.20
     fiber
    1.08
     fibre
    1.05
     optics
    0.95
    fill
    0.79
     fibers
    0.78
    opt
    0.76
     tracts
    0.74
    Activations Density 0.005%

    No Known Activations