© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    personal experiences or actions performed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal empowerment and independence

    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
    Products
    -0.71
    edu
    -0.70
    also
    -0.64
    ADVERTISEMENT
    -0.64
    https
    -0.63
    Lee
    -0.62
    awei
    -0.61
    Raw
    -0.60
    NH
    -0.59
    Normal
    -0.59
    POSITIVE LOGITS
     notwithstanding
    0.81
     preferably
    0.77
     imagin
    0.75
     whatever
    0.75
     maybe
    0.75
     perhaps
    0.72
     unsus
    0.70
     guiActive
    0.69
     oneself
    0.68
     flickering
    0.67
    Activations Density 0.736%

    No Known Activations