© 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. 10-RES-JB
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinion and political support

    oai_token-act-pair · gpt-3.5-turbo

    important political discussions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enh
    -0.77
    agate
    -0.75
    database
    -0.73
     Accessed
    -0.71
    aunder
    -0.71
     alias
    -0.68
    icide
    -0.66
    ocalypse
    -0.65
    worm
    -0.65
    apeake
    -0.65
    POSITIVE LOGITS
     supporters
    1.36
     undecided
    1.34
     voters
    1.32
     sentiment
    1.32
     sentiments
    1.28
     proponents
    1.28
     commenters
    1.27
     respondents
    1.26
     unanim
    1.23
     detractors
    1.22
    Activations Density 0.632%

    No Known Activations