© 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. 612
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideology and political beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of national identity or nationalism

    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
    conom
    -0.78
    ãģ®éŃĶ
    -0.76
    astern
    -0.74
    ---------------
    -0.74
    ortium
    -0.72
    Boss
    -0.72
    Brand
    -0.69
    lings
    -0.68
    flix
    -0.66
    Snake
    -0.65
    POSITIVE LOGITS
    ized
    0.97
    ally
    0.92
    ities
    0.92
    ism
    0.88
    ity
    0.87
    ational
    0.86
    ists
    0.84
    ist
    0.84
    izational
    0.83
    ité
    0.81
    Activations Density 0.015%

    No Known Activations