© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 8987
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of imminent danger or crisis

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state or condition of being on the verge or at a critical point

    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
    lement
    -0.84
    thood
    -0.74
    bots
    -0.73
    arson
    -0.64
    upon
    -0.63
    cles
    -0.63
     IMAGES
    -0.62
    bourg
    -0.62
    rand
    -0.61
    ovember
    -0.61
    POSITIVE LOGITS
     verge
    1.30
     brink
    1.16
     forefront
    1.12
     lookout
    1.09
     bandwagon
    0.93
     sidelines
    0.92
     doorstep
    0.90
     periphery
    0.90
     heels
    0.87
     ground
    0.87
    Activations Density 0.135%

    No Known Activations