© 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. 2-RES-JB
    6. 4132
    Prev
    Next
    INDEX
    Explanations

    names related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Abdel" and other related names, indicating a focus on specific individuals

    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
     Bermuda
    -0.86
     Wildcats
    -0.82
     Scots
    -0.78
     Palmer
    -0.78
     UNIVERS
    -0.78
     Mahar
    -0.77
     Hawaiian
    -0.76
     Cardinals
    -0.75
     Counsel
    -0.75
     Tycoon
    -0.75
    POSITIVE LOGITS
    afia
    1.02
     Abdel
    0.97
     challeng
    0.84
     arrang
    0.84
    iques
    0.81
    aton
    0.78
     unden
    0.78
     eaves
    0.77
    iqu
    0.77
    reon
    0.76
    Activations Density 0.012%

    No Known Activations