© 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. 8-RES-JB
    11. 9466
    Prev
    Next
    INDEX
    Explanations

    words related to cleaning or removing something forcefully

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "sweeping" or "sweeps" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     willpower
    -0.64
     Founding
    -0.63
     bonding
    -0.62
     bonded
    -0.62
    nect
    -0.62
     Palestin
    -0.62
    xus
    -0.60
     Minotaur
    -0.60
     recomm
    -0.59
     Countdown
    -0.58
    POSITIVE LOGITS
    stakes
    1.95
     away
    0.92
    restling
    0.91
    sheets
    0.88
    hurst
    0.88
    aways
    0.84
    away
    0.82
    shots
    0.80
     Away
    0.80
     aside
    0.79
    Activations Density 0.034%

    No Known Activations