© 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 EvalsExportsinterp-engineNEWAPI 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. 10386
    Prev
    Next
    INDEX
    Explanations

    phrases related to intimate personal interactions

    oai_token-act-pair · gpt-3.5-turbo

    patterns of sequences and interactions between subjects

    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
     inher
    -0.67
    è¯
    -0.67
    represent
    -0.65
     equals
    -0.65
    Thumbnail
    -0.65
    resents
    -0.65
     equivalent
    -0.64
    æĺ¯
    -0.64
     enshr
    -0.64
    arers
    -0.63
    POSITIVE LOGITS
    Eventually
    1.85
     Eventually
    1.81
     eventually
    1.33
     Soon
    1.15
     Occasionally
    1.14
    until
    1.12
     Finally
    1.10
     Slowly
    1.10
     gradually
    1.09
    Soon
    1.09
    Activations Density 0.687%

    No Known Activations