© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    quantitative terms relating to changes or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant changes or trends

    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
    parts
    -0.79
    iddles
    -0.79
    words
    -0.77
    agents
    -0.77
    mates
    -0.72
    Tickets
    -0.71
     honors
    -0.71
    posts
    -0.70
    Instruct
    -0.69
    grounds
    -0.68
    POSITIVE LOGITS
     tendency
    1.37
     shortage
    1.36
     resurgence
    1.33
     surge
    1.30
     decrease
    1.29
     plethora
    1.29
     flurry
    1.26
     spate
    1.24
     lack
    1.22
     slowdown
    1.20
    Activations Density 0.335%

    No Known Activations