© 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. 7-RES-JB
    11. 23900
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events or voting actions

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     workspace
    -0.78
     negoti
    -0.78
     careg
    -0.74
     gou
    -0.72
     playbook
    -0.72
     warr
    -0.72
     purse
    -0.71
     babys
    -0.69
     alley
    -0.69
     halls
    -0.68
    POSITIVE LOGITS
     Specifically
    1.34
     Indeed
    1.30
     Accordingly
    1.30
     Consequently
    1.25
     Furthermore
    1.22
     Moreover
    1.21
     Therefore
    1.21
     However
    1.21
     Whereas
    1.19
     According
    1.17
    Activations Density 0.638%

    No Known Activations