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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7880
    Prev
    Next
    INDEX
    Explanations

    terms related to extremist groups and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to extremist ideologies and 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
    esville
    -0.83
     Minotaur
    -0.81
    eries
    -0.79
    sburgh
    -0.79
    yards
    -0.77
    rol
    -0.72
    porter
    -0.71
    yard
    -0.71
    otaur
    -0.71
    ust
    -0.71
    POSITIVE LOGITS
     extremist
    1.01
     extremists
    1.00
     extremism
    0.99
     ideology
    0.98
     ideologies
    0.95
     Islamist
    0.86
     fringe
    0.86
     ide
    0.86
     tendencies
    0.84
     guiActiveUn
    0.84
    Activations Density 0.016%

    No Known Activations