© 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. 12641
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation or judgment of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to classic literature and media, particularly those that evoke nostalgia or established cultural significance

    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
    onds
    -0.73
    assadors
    -0.70
    encers
    -0.69
    ievers
    -0.69
    esville
    -0.69
    ieving
    -0.68
     employers
    -0.68
    rals
    -0.67
    aires
    -0.67
    angering
    -0.67
    POSITIVE LOGITS
     dated
    1.13
     unfinished
    1.03
     derivative
    0.97
     incomplete
    0.96
     titled
    0.93
    dated
    0.91
     spoiler
    0.91
     plagiar
    0.90
     rewritten
    0.90
     kinda
    0.89
    Activations Density 0.477%

    No Known Activations