© 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. 9-RES-JB
    11. 7361
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    indications of causality or significant changes in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilar
    -0.78
    noticed
    -0.66
    USS
    -0.65
    ebted
    -0.63
     regretted
    -0.63
    ONDON
    -0.61
    OA
    -0.60
     hairs
    -0.58
    Sus
    -0.58
     ambitious
    -0.58
    POSITIVE LOGITS
     ALWAYS
    0.83
     abound
    0.83
     flourish
    0.82
     dictate
    0.82
     everywhere
    0.80
     perv
    0.78
     trump
    0.77
     always
    0.73
     democrat
    0.72
    always
    0.70
    Activations Density 0.424%

    No Known Activations