© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and health implications, as well as commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their context in sentences

    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
    ascus
    -0.80
    anmar
    -0.79
    ãĥĵ
    -0.77
     carbohyd
    -0.71
    ersive
    -0.70
     satell
    -0.70
     corrid
    -0.69
    bleacher
    -0.68
     earthqu
    -0.66
    ŃĶ
    -0.66
    POSITIVE LOGITS
     Similarly
    1.47
     Likewise
    1.41
     Conversely
    1.37
     Also
    1.36
     Additionally
    1.34
     Therefore
    1.32
     Alternatively
    1.30
     Furthermore
    1.29
     Hence
    1.23
     Lastly
    1.23
    Activations Density 0.590%

    No Known Activations