© 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. 18753
    Prev
    Next
    INDEX
    Explanations

    political titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of council-related titles or terms

    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
     Roosevelt
    -0.73
     Haram
    -0.68
    ARS
    -0.67
     Gamb
    -0.67
    âĵĺ
    -0.66
    çīĪ
    -0.66
     Patriot
    -0.65
    ENGTH
    -0.64
     rooting
    -0.63
     Sheep
    -0.62
    POSITIVE LOGITS
    cill
    1.40
     Coun
    1.27
    Coun
    1.16
    cil
    0.92
    selling
    0.90
    plin
    0.82
     councillors
    0.81
    itivity
    0.81
    nai
    0.78
     councillor
    0.78
    Activations Density 0.009%

    No Known Activations