© 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. 8-RES-JB
    11. 10343
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing governmental actions or agendas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     besides
    -0.76
    atoon
    -0.74
    Alert
    -0.72
    LOD
    -0.70
    âĸł
    -0.69
     owing
    -0.67
     beforehand
    -0.67
    escription
    -0.67
    \'
    -0.67
    iffe
    -0.67
    POSITIVE LOGITS
     slightest
    1.25
    ocratic
    1.22
    ocracy
    1.20
    ocrats
    1.11
     nation
    1.09
     wealthiest
    1.09
     greatest
    1.03
    ologies
    1.03
     poorest
    1.03
     electorate
    1.02
    Activations Density 0.782%

    No Known Activations