© 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. 9-RES-JB
    11. 10100
    Prev
    Next
    INDEX
    Explanations

    mentions of specific American presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual identified as "President."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overload
    -0.71
     filler
    -0.70
     subdivision
    -0.68
     neutron
    -0.68
     Bulgarian
    -0.67
     reproduction
    -0.67
     JPEG
    -0.65
     scrim
    -0.64
     utilization
    -0.64
     capacitor
    -0.63
    POSITIVE LOGITS
    realDonaldTrump
    1.22
    Jr
    1.04
    cffffcc
    0.97
    shall
    0.91
    issance
    0.90
    ï¸ı
    0.86
    ï
    0.84
    care
    0.82
    ðŁ
    0.82
    tre
    0.80
    Activations Density 0.152%

    No Known Activations