© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 15378
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to seriousness or severity

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that convey the seriousness and severity of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uter
    -0.72
     recess
    -0.70
    ram
    -0.66
    places
    -0.64
     passage
    -0.64
     openings
    -0.63
    imentary
    -0.62
    vice
    -0.62
    nell
    -0.61
     Mass
    -0.61
    POSITIVE LOGITS
     seriousness
    1.25
    iness
    1.11
    fulness
    0.93
     severity
    0.85
     urgency
    0.81
    udence
    0.81
    ;;;;
    0.79
    lessness
    0.78
    anguage
    0.77
    ailability
    0.76
    Activations Density 0.017%

    No Known Activations