© 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. 3-RES-JB
    11. 15479
    Prev
    Next
    INDEX
    Explanations

    phrases related to political slogans

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to political campaigns and slogans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discharge
    -0.78
     constitu
    -0.75
     tremend
    -0.71
    éĹ
    -0.70
    )].
    -0.70
    RAY
    -0.68
     exha
    -0.67
     resonance
    -0.66
     circulation
    -0.66
    è£
    -0.66
    POSITIVE LOGITS
    ings
    1.00
    aways
    0.94
    away
    0.93
    ables
    0.91
     Yourself
    0.89
     Your
    0.86
    ments
    0.82
    Point
    0.80
    zon
    0.79
     Them
    0.78
    Activations Density 0.149%

    No Known Activations