© 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 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. 3-RES-JB
    11. 3987
    Prev
    Next
    INDEX
    Explanations

    phrases related to severity or seriousness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to seriousness and severity of situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uter
    -0.71
    ram
    -0.71
    rams
    -0.65
    rote
    -0.64
    iverse
    -0.63
    cells
    -0.63
    wash
    -0.62
    vice
    -0.62
    places
    -0.62
    imentary
    -0.61
    POSITIVE LOGITS
    iness
    1.07
     seriousness
    1.02
    fulness
    0.95
     severity
    0.86
    worthiness
    0.83
    uality
    0.83
    anguage
    0.82
    lessness
    0.80
    iencies
    0.78
    staking
    0.77
    Activations Density 0.030%

    No Known Activations