© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14793
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives, especially relating to more or less

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "more" or "greater" in 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
     Dreams
    -0.79
    æ©
    -0.75
     Contracts
    -0.74
     Procedures
    -0.74
    rities
    -0.74
    another
    -0.72
     Projects
    -0.70
     Travels
    -0.69
     Releases
    -0.69
     Errors
    -0.68
    POSITIVE LOGITS
     nuanced
    1.19
     manageable
    1.15
     sophisticated
    1.13
    than
    1.12
     expansive
    1.12
     cohesive
    1.09
     efficient
    1.09
     comprehensive
    1.08
     complicated
    1.08
     aggressive
    1.08
    Activations Density 0.039%

    No Known Activations