© 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. 12424
    Prev
    Next
    INDEX
    Explanations

    mentions of a political party named AAP

    oai_token-act-pair · gpt-3.5-turbo

    references to the AAP (Aam Aadmi Party) and its leadership

    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
    ãĤ¹ãĥĪ
    -0.78
    wagen
    -0.78
     Robertson
    -0.75
    ãĥĩãĤ£
    -0.71
     Luthor
    -0.71
     Glou
    -0.69
    bred
    -0.68
    Roberts
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ãĤ·ãĥ£
    -0.65
    POSITIVE LOGITS
    daq
    1.10
    jriwal
    1.01
    ilon
    0.98
    IUM
    0.84
    ointed
    0.83
     AAP
    0.80
    ilan
    0.78
    ILY
    0.77
    ointment
    0.76
    vantage
    0.75
    Activations Density 0.008%

    No Known Activations