© 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. 6-RES-JB
    11. 9652
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic work or papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.70
    Layer
    -0.69
    Iterator
    -0.67
    äºĶ
    -0.65
    aurus
    -0.65
    bear
    -0.63
     sucks
    -0.63
    Bi
    -0.61
    LOG
    -0.61
    beard
    -0.61
    POSITIVE LOGITS
     behalf
    1.17
     basis
    1.11
     eve
    1.01
     topic
    0.99
     occasion
    0.98
     outskirts
    0.96
     aforementioned
    0.94
     sidelines
    0.91
     occasions
    0.88
     merits
    0.87
    Activations Density 0.181%

    No Known Activations