© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    time-related phrases with precision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" across various contexts

    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
    RGB
    -0.68
     worshipped
    -0.66
    acho
    -0.65
     besides
    -0.65
     withstand
    -0.63
     Tradable
    -0.63
    STON
    -0.62
     AMERICA
    -0.62
     distinguishes
    -0.62
    ivas
    -0.60
    POSITIVE LOGITS
     beginning
    1.37
     end
    1.32
     onset
    1.29
     outset
    1.27
     earliest
    1.22
     arrival
    1.19
     advent
    1.09
     conclusion
    1.09
     expiration
    1.06
     start
    1.05
    Activations Density 0.211%

    No Known Activations