© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10094
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Donald Trump" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Donald Trump."

    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
     sidx
    -0.69
    Completed
    -0.68
    nexus
    -0.67
     guiActiveUnfocused
    -0.67
    FY
    -0.65
     forth
    -0.65
     urgency
    -0.63
    MQ
    -0.63
    Member
    -0.63
     gag
    -0.63
    POSITIVE LOGITS
     Trump
    1.22
     Donald
    1.08
    son
    1.04
    Trump
    0.92
    Donald
    0.91
     Glover
    0.91
    trump
    0.91
     Rodham
    0.81
    ottesville
    0.80
    dinand
    0.80
    Activations Density 0.015%

    No Known Activations