© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    phrases related to specialized skills or services

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "special" and related terms

    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
     favour
    -0.84
     breakup
    -0.71
     disinteg
    -0.71
     Cah
    -0.71
     contag
    -0.71
     erosion
    -0.70
     inev
    -0.68
     collapse
    -0.66
     favor
    -0.65
     blockade
    -0.63
    POSITIVE LOGITS
    owship
    0.87
    ESSION
    0.87
    iaries
    0.85
    ortment
    0.78
    itions
    0.78
    lear
    0.77
    BILITIES
    0.77
    ctors
    0.76
    ãĤ¹ãĥĪ
    0.76
    onnaissance
    0.75
    Activations Density 0.105%

    No Known Activations