© 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. 20814
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or strategic interests

    oai_token-act-pair · gpt-3.5-turbo

    references to various interests, particularly in a political or economic context

    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
    ãĤ¨ãĥ«
    -0.81
    BuyableInstoreAndOnline
    -0.70
    aan
    -0.70
    ergy
    -0.69
    ones
    -0.68
    bird
    -0.68
    aston
    -0.67
    berry
    -0.66
    Bird
    -0.64
    adapt
    -0.64
    POSITIVE LOGITS
     interests
    1.04
    reprene
    0.98
     agendas
    0.78
    hops
    0.77
     agenda
    0.76
     territ
    0.74
    kaya
    0.74
     benefic
    0.72
     Lobby
    0.71
    afe
    0.71
    Activations Density 0.024%

    No Known Activations