© 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. 20779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating takeovers or control

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take over."

    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
    ero
    -0.66
    WARE
    -0.66
    Detect
    -0.63
    Forward
    -0.63
     Detect
    -0.63
    IAS
    -0.62
    area
    -0.62
    ////////////////////////////////
    -0.60
    osity
    -0.60
    Mini
    -0.60
    POSITIVE LOGITS
    drive
    0.93
    tones
    0.92
    lord
    0.85
    haul
    0.77
    irgin
    0.76
     reins
    0.75
    stocks
    0.75
    lain
    0.74
    ran
    0.72
    react
    0.71
    Activations Density 0.018%

    No Known Activations