© 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. 16050
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiations or exchanges, especially involving favors or deals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to professional or formal 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
    NK
    -0.84
    enhagen
    -0.80
    PK
    -0.77
    SY
    -0.75
    Shin
    -0.75
    æĪ¦
    -0.72
    STD
    -0.72
    isky
    -0.72
     NK
    -0.71
    BP
    -0.71
    POSITIVE LOGITS
     quo
    0.84
     faire
    0.77
     patri
    0.72
     riches
    0.70
     gard
    0.67
     bene
    0.66
    ciation
    0.66
     pas
    0.65
     gener
    0.64
     ter
    0.64
    Activations Density 0.116%

    No Known Activations