© 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. 17755
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming, specifically focusing on instructions, examples, and technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce explanations or examples

    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
     Rodham
    -0.80
    AFP
    -0.73
     presided
    -0.64
     Guant
    -0.63
     kindred
    -0.61
     UNCLASSIFIED
    -0.60
     Salman
    -0.56
     Osama
    -0.55
    Putin
    -0.54
     Cheney
    -0.54
    POSITIVE LOGITS
    Example
    0.95
     drawback
    0.89
     downside
    0.82
     disadvantage
    0.79
     Example
    0.78
    oret
    0.78
     disadvantages
    0.77
     example
    0.74
    yip
    0.73
    entimes
    0.71
    Activations Density 0.635%

    No Known Activations