© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2427
    Prev
    Next
    INDEX
    Explanations

    text related to software code, particularly involving manipulating, storing, and accessing data as well as parsing and processing resources

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to data manipulation and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovation
    -0.78
    occup
    -0.76
    otomy
    -0.75
    chance
    -0.73
    fare
    -0.72
    utch
    -0.72
    Lyn
    -0.70
    dra
    -0.69
    igmatic
    -0.69
    nec
    -0.68
    POSITIVE LOGITS
     JSON
    1.28
     files
    1.27
     XML
    1.23
     directories
    1.22
     URLs
    1.20
     strings
    1.15
     arbitrary
    1.15
     documents
    1.14
     datasets
    1.12
     objects
    1.12
    Activations Density 0.258%

    No Known Activations