© 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. 6-RES-JB
    11. 17374
    Prev
    Next
    INDEX
    Explanations

    political figures and their related activities or positions

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or sentiments associated with various political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.83
    DragonMagazine
    -0.77
     ransom
    -0.76
     prompt
    -0.71
    obyl
    -0.70
     glean
    -0.70
     intrinsic
    -0.69
     structure
    -0.69
     poets
    -0.66
     astronomers
    -0.66
    POSITIVE LOGITS
    California
    1.05
    Portland
    1.03
    Seattle
    1.02
    Calif
    0.96
    Minnesota
    0.95
    Washington
    0.95
    Nation
    0.95
    Mont
    0.92
    nom
    0.92
    East
    0.91
    Activations Density 0.042%

    No Known Activations