© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    keywords related to political organizations, affiliations, and events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the AFL-CIO organization

    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
    stadt
    -0.83
    ysis
    -0.70
     Nicarag
    -0.68
    leigh
    -0.63
     Anat
    -0.62
     advis
    -0.61
    theless
    -0.60
     Guatem
    -0.59
     DeL
    -0.59
     Hole
    -0.58
    POSITIVE LOGITS
    izophren
    0.80
    Lenin
    0.73
    actionDate
    0.72
    amins
    0.66
    affiliated
    0.65
    APP
    0.64
    learn
    0.64
    Unity
    0.63
    errilla
    0.62
    riter
    0.62
    Activations Density 0.126%

    No Known Activations