© 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. 10-RES-JB
    11. 16606
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing and categorizing items or information

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to organization and categorization of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibur
    -0.69
    efe
    -0.60
     abroad
    -0.58
    enance
    -0.58
     firsthand
    -0.58
     unethical
    -0.56
     Stamford
    -0.55
     unknow
    -0.55
     vehemently
    -0.55
     staunch
    -0.55
    POSITIVE LOGITS
     grouped
    1.11
     alphabet
    1.07
    each
    1.04
     grouping
    1.02
     numbered
    1.01
     parentheses
    1.00
     columns
    1.00
    numbered
    0.98
     Lists
    0.95
     rows
    0.93
    Activations Density 0.607%

    No Known Activations