© 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. 10-RES-JB
    11. 13819
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to being at a perceived risk or critical point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating risk or significant concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTWARE
    -0.69
    OTHER
    -0.67
    planes
    -0.66
    cert
    -0.64
    aceutical
    -0.62
    behavior
    -0.58
    TEXT
    -0.57
    mingham
    -0.56
     dir
    -0.56
    Thumbnail
    -0.55
    POSITIVE LOGITS
     least
    1.25
     odds
    1.20
     risk
    1.16
     pains
    1.15
     fault
    1.11
    yp
    1.09
     liberty
    1.07
     logger
    1.04
     stake
    1.00
     variance
    0.94
    Activations Density 0.065%

    No Known Activations