© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5558
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to public engagement or feedback processes

    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
    kid
    -0.70
     underage
    -0.69
     jack
    -0.67
     Poverty
    -0.65
    aunder
    -0.63
    earable
    -0.61
     Everywhere
    -0.61
    hett
    -0.61
     cel
    -0.60
    azon
    -0.60
    POSITIVE LOGITS
     answers
    1.01
     clarification
    0.99
     deliber
    0.96
     reasoned
    0.95
     opportunity
    0.95
     explanation
    0.93
     reconsider
    0.90
     insight
    0.88
     discussion
    0.87
     debate
    0.87
    Activations Density 0.709%

    No Known Activations