© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4375
    Prev
    Next
    INDEX
    Explanations

    political terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political platforms and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UNESCO
    -0.80
    uckland
    -0.78
     Yi
    -0.78
     Qing
    -0.76
    sterdam
    -0.71
    RAL
    -0.70
     LIA
    -0.69
    ANK
    -0.68
    YA
    -0.68
     Shu
    -0.67
    POSITIVE LOGITS
     speeches
    1.12
     stances
    1.03
    cand
    1.02
     endors
    1.00
     endorsements
    1.00
    clinton
    0.96
     rhetoric
    0.93
     charisma
    0.93
     foe
    0.90
     frontrunner
    0.86
    Activations Density 0.338%

    No Known Activations