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

    Neuronpedia

    Jacobian LensNEW
    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. 18344
    Prev
    Next
    INDEX
    Explanations

    phrases related to official appointments or resignations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political positions and swearing-in ceremonies

    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
    onies
    -0.73
    PsyNetMessage
    -0.73
    raq
    -0.72
    aceae
    -0.72
    ournals
    -0.71
    isks
    -0.69
    products
    -0.67
    ubb
    -0.67
    onen
    -0.65
    ramid
    -0.65
    POSITIVE LOGITS
     president
    1.74
     chairman
    1.55
     chancellor
    1.51
     mayor
    1.47
     governor
    1.44
     secretary
    1.38
     chief
    1.37
     President
    1.36
     ambassador
    1.35
     honorary
    1.35
    Activations Density 0.328%

    No Known Activations