© 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. 6-RES-JB
    11. 14559
    Prev
    Next
    INDEX
    Explanations

    phrases related to public statements or comments

    oai_token-act-pair · gpt-3.5-turbo

    statements or remarks made by individuals in positions of authority or influence

    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
    ource
    -0.72
    oen
    -0.65
    rollment
    -0.64
    ioxide
    -0.63
    ertain
    -0.63
    vari
    -0.60
    eers
    -0.60
     Currently
    -0.60
    properties
    -0.59
    ric
    -0.59
    POSITIVE LOGITS
     fateful
    0.84
     memorable
    0.69
     aftermath
    0.66
    rompt
    0.64
    ï¸
    0.63
    æµ
    0.63
     transpired
    0.62
     botched
    0.61
     Charlottesville
    0.60
    Thumbnail
    0.60
    Activations Density 0.859%

    No Known Activations