© 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. 0-RES-JB
    11. 11373
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures or events, particularly names ending in 'ek'

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of a specific suffix or pattern in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MMR
    -0.65
     widespread
    -0.61
     Civil
    -0.60
     consideration
    -0.58
     NAACP
    -0.58
     Gravity
    -0.58
     constituent
    -0.58
     Surface
    -0.58
     conting
    -0.57
     picnic
    -0.57
    POSITIVE LOGITS
    ek
    4.38
    eks
    2.70
    eker
    2.08
    eking
    1.97
    eka
    1.77
    eki
    1.71
    ec
    1.67
    ech
    1.59
    ik
    1.31
    eg
    1.28
    Activations Density 0.011%

    No Known Activations