© 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. 7-RES-JB
    11. 23760
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming languages and formats, specifically Markdown and BibTeX

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and coding formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mounted
    -0.82
    charg
    -0.77
     refuel
    -0.73
     Gear
    -0.73
     Carnage
    -0.70
    GV
    -0.69
     raided
    -0.69
    osponsors
    -0.68
    olphins
    -0.68
     renters
    -0.68
    POSITIVE LOGITS
     diction
    1.44
     textbooks
    1.41
     aloud
    1.34
     dictionary
    1.27
     poetry
    1.23
     texts
    1.23
     encyclopedia
    1.23
     grammar
    1.21
     translation
    1.19
     language
    1.17
    Activations Density 1.017%

    No Known Activations