© 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. 7-RES-JB
    11. 9537
    Prev
    Next
    INDEX
    Explanations

    instances related to ripping or tearing actions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rip"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beit
    -0.76
     MacArthur
    -0.73
    äºĶ
    -0.71
    ADRA
    -0.69
     Gemini
    -0.63
    OTE
    -0.62
    ccording
    -0.60
    ĨĴ
    -0.59
    BIP
    -0.59
    åį
    -0.58
    POSITIVE LOGITS
    hest
    0.95
    away
    0.92
    rodu
    0.90
    aways
    0.86
     rip
    0.85
    offs
    0.83
    ety
    0.81
    hend
    0.81
    eness
    0.78
     ripped
    0.77
    Activations Density 0.016%

    No Known Activations