© 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. 7510
    Prev
    Next
    INDEX
    Explanations

    phrases indicating compositions or makeup of groups or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote composition or elements of a group

    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
    ilings
    -0.76
    WT
    -0.68
    hawks
    -0.64
    oos
    -0.63
    hound
    -0.62
    apon
    -0.62
    mob
    -0.60
    thur
    -0.59
     Sands
    -0.58
     Dull
    -0.58
    POSITIVE LOGITS
     consist
    0.87
     solely
    0.85
    encies
    0.83
     chiefly
    0.82
    ertodd
    0.79
    itute
    0.77
     principally
    0.76
     mainly
    0.75
    ãĥĦ
    0.74
    alion
    0.74
    Activations Density 0.015%

    No Known Activations