© 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. 7-RES-JB
    11. 19210
    Prev
    Next
    INDEX
    Explanations

    words related to strong negative emotions and reactions towards specific events or situations, especially in a communal context

    oai_token-act-pair · gpt-3.5-turbo

    references to feelings of outrage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Password
    -0.74
    ession
    -0.71
    ramer
    -0.71
    lasses
    -0.69
    omething
    -0.68
    wagen
    -0.67
     cleaner
    -0.66
     livest
    -0.66
     Solitaire
    -0.65
    uchin
    -0.64
    POSITIVE LOGITS
    ously
    1.21
    iously
    0.96
     indignation
    0.95
    storms
    0.84
     uproar
    0.82
    storm
    0.79
     outcry
    0.78
     against
    0.74
     outrage
    0.74
    uously
    0.73
    Activations Density 0.029%

    No Known Activations