© 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. 2-RES-JB
    11. 11679
    Prev
    Next
    INDEX
    Explanations

    words related to movements or ideologies associated with anarchy or anarchist beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to anarchism and its ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bred
    -0.86
     Grind
    -0.72
    lease
    -0.68
    Wo
    -0.67
    Score
    -0.67
    %%%%
    -0.65
    pless
    -0.64
    uez
    -0.63
    pered
    -0.63
     HPV
    -0.62
    POSITIVE LOGITS
     anarchist
    1.12
     anarchists
    1.06
     anarchism
    1.02
     Anarch
    0.96
     insurrection
    0.88
     communists
    0.83
     revolt
    0.83
    ©¶æ¥µ
    0.82
     chic
    0.79
     anarchy
    0.78
    Activations Density 0.013%

    No Known Activations