© 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. 4-RES-JB
    11. 17072
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to different topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate upcoming actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvant
    -0.58
     UNCLASSIFIED
    -0.57
     skelet
    -0.55
     exting
    -0.54
    CONCLUS
    -0.51
    Conclusion
    -0.49
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.49
     pse
    -0.49
    âķIJ
    -0.48
     [*
    -0.47
    POSITIVE LOGITS
     âĢİ
    0.60
     Posted
    0.59
    20439
    0.58
     [âĢ¦]
    0.58
     âĢº
    0.57
    âĢİ
    0.53
     frontman
    0.47
     Updated
    0.46
     Halifax
    0.45
     Published
    0.45
    Activations Density 5.842%

    No Known Activations