© 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. 10-RES-JB
    11. 13670
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, or measures being implemented

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in place" or variations of it

    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
    ensor
    -0.68
    cade
    -0.65
    iday
    -0.62
    mini
    -0.61
     forgiven
    -0.60
    idays
    -0.60
    nic
    -0.60
    ieth
    -0.59
    ragon
    -0.59
     spo
    -0.59
    POSITIVE LOGITS
     place
    1.52
     effect
    1.16
    place
    1.05
    activated
    1.00
     existence
    1.00
    effect
    0.97
    effic
    0.95
    operative
    0.92
    ked
    0.90
     operation
    0.85
    Activations Density 0.170%

    No Known Activations