© 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. 9-RES-JB
    11. 4629
    Prev
    Next
    INDEX
    Explanations

    phrases related to community issues and societal concerns

    oai_token-act-pair · gpt-3.5-turbo

    quotes or reported speech from individuals

    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
     completed
    -0.89
     attained
    -0.85
     precise
    -0.83
     successor
    -0.83
     subscript
    -0.82
     formally
    -0.81
     exqu
    -0.80
     canonical
    -0.79
     sequential
    -0.79
     retained
    -0.78
    POSITIVE LOGITS
    Parents
    1.21
     Parents
    1.06
     Families
    1.05
    Kids
    1.04
     Especially
    1.03
    Mayor
    1.03
    Girls
    1.01
    People
    1.01
     Communities
    1.00
    Especially
    0.98
    Activations Density 0.840%

    No Known Activations