© 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. 10742
    Prev
    Next
    INDEX
    Explanations

    references to activities or circumstances related to investigations, potential dangers, and legal implications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to security and evidence of wrongdoing

    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
     reins
    -0.69
     bitterly
    -0.67
     wheelchair
    -0.66
    raphics
    -0.65
    adobe
    -0.64
    utterstock
    -0.64
    lished
    -0.63
     Cheap
    -0.60
     Dram
    -0.59
     partName
    -0.58
    POSITIVE LOGITS
    worthiness
    1.09
     tampering
    1.06
     involvement
    1.04
     contamination
    1.03
     irregularities
    1.03
     wrongdoing
    1.03
     imminent
    1.01
     violations
    0.96
     lurking
    0.95
     discrepancies
    0.93
    Activations Density 0.486%

    No Known Activations