© 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. 7339
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing depth or complexity

    oai_token-act-pair · gpt-3.5-turbo

    comparisons suggesting complexity or depth

    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
    ella
    -0.75
    taboola
    -0.75
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.74
    âĹ¼
    -0.74
    Winged
    -0.71
    ECT
    -0.69
    soType
    -0.69
    ALLY
    -0.68
    Used
    -0.66
    ãģ®éŃĶ
    -0.66
    POSITIVE LOGITS
     mere
    1.21
     merely
    1.11
     simply
    1.10
     just
    0.91
     superficial
    0.89
     meets
    0.87
     simple
    0.87
     brute
    0.80
     purely
    0.80
     ordinary
    0.78
    Activations Density 0.129%

    No Known Activations