© 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. 15817
    Prev
    Next
    INDEX
    Explanations

    phrases related to various aspects of life and activities

    oai_token-act-pair · gpt-3.5-turbo

    patterns or phrases that highlight connections and relationships between ideas or concepts

    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
    umbn
    -0.76
    Optional
    -0.75
    ses
    -0.71
    lishes
    -0.70
    FM
    -0.68
    uple
    -0.65
    Ear
    -0.65
    iots
    -0.64
    usk
    -0.64
    tein
    -0.63
    POSITIVE LOGITS
     moreover
    1.17
     rightfully
    1.11
     consequently
    1.09
     therefore
    1.08
     hence
    1.07
     fortunately
    1.07
     luckily
    1.07
     therein
    1.04
     furthermore
    1.03
     thus
    1.01
    Activations Density 0.225%

    No Known Activations