© 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. 7429
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their attributes or actions

    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
     Nationwide
    -0.81
    ļéĨĴ
    -0.71
     §§
    -0.70
     Checking
    -0.70
     Using
    -0.68
     Horses
    -0.66
    odder
    -0.66
     Regions
    -0.65
    £ı
    -0.64
    aspx
    -0.63
    POSITIVE LOGITS
     embodies
    1.50
     deserves
    1.34
     represents
    1.20
     deserved
    1.16
     embody
    1.16
     epit
    1.10
     inspires
    1.09
     undeniably
    1.04
     belongs
    1.03
     certainly
    1.03
    Activations Density 0.381%

    No Known Activations