© 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. 4-RES-JB
    11. 15799
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative emotions and controversies

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anger or negative emotions towards individuals or groups

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

    No Comments

    Negative Logits
     reconc
    -0.65
     Staten
    -0.65
    essions
    -0.65
     Sacrifice
    -0.65
     Fulton
    -0.63
     Piano
    -0.61
    ipeg
    -0.60
     stocks
    -0.60
     Spaces
    -0.60
    ramid
    -0.60
    POSITIVE LOGITS
    terness
    0.97
     ire
    0.93
    fulness
    0.85
     wrath
    0.85
    hound
    0.81
    PLA
    0.79
    wart
    0.78
    ãĥķãĤ¡
    0.77
    nery
    0.76
    baugh
    0.75
    Activations Density 0.019%

    No Known Activations