© 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. 11-RES-JB
    11. 20502
    Prev
    Next
    INDEX
    Explanations

    names or titles related to presidents or leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "president" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Medium
    -0.63
    Definition
    -0.61
    γ
    -0.59
    DEN
    -0.58
    TOR
    -0.57
     darkness
    -0.55
    ASED
    -0.55
     newcomers
    -0.55
     Nightmares
    -0.55
     tru
    -0.55
    POSITIVE LOGITS
    ially
    1.13
    ial
    1.09
    clinton
    1.09
    aroo
    0.87
    iors
    0.85
     emer
    0.85
    manship
    0.84
    eki
    0.81
    esses
    0.81
    dom
    0.78
    Activations Density 0.056%

    No Known Activations