© 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. 24220
    Prev
    Next
    INDEX
    Explanations

    words related to trouble or problematic situations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific programs or concepts related to financial or social assistance, particularly focusing on "Troubled" and associated themes

    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
    ļéĨĴ
    -0.85
    assetsadobe
    -0.74
    nesota
    -0.72
    çīĪ
    -0.68
    )=(
    -0.68
    76561
    -0.68
    /(
    -0.67
    */(
    -0.67
    åŃ
    -0.67
    ))))
    -0.64
    POSITIVE LOGITS
     Trou
    1.03
    bles
    0.98
    bled
    0.77
    ament
    0.77
    alore
    0.77
    ilitation
    0.72
    autions
    0.70
     vets
    0.70
    rupted
    0.69
    cffffcc
    0.69
    Activations Density 0.018%

    No Known Activations