© 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. 0-RES-JB
    6. 7827
    Prev
    Next
    INDEX
    Explanations

    names of political figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people, particularly those in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cal
    -0.84
    Angelo
    -0.81
     Angelo
    -0.73
    ãĥ¯
    -0.70
    pie
    -0.69
    vern
    -0.69
     virt
    -0.69
    ãĤº
    -0.67
    entimes
    -0.66
    cia
    -0.66
    POSITIVE LOGITS
     Hull
    1.64
     HRC
    1.64
     HH
    1.59
     Huckabee
    1.56
     Huff
    1.52
     Harding
    1.52
     HHS
    1.52
     Hed
    1.51
     Hanson
    1.50
     Hil
    1.49
    Activations Density 0.085%

    No Known Activations