© 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. 20578
    Prev
    Next
    INDEX
    Explanations

    phrases indicating belonging or being part of a group or community

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize belonging or being part of a group

    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
     assumes
    -0.66
     ceilings
    -0.65
    ptive
    -0.65
     incurred
    -0.63
     withd
    -0.62
     directs
    -0.61
     spouses
    -0.60
    culosis
    -0.60
    iasis
    -0.59
    ants
    -0.58
    POSITIVE LOGITS
    ¬¼
    0.72
     the
    0.70
     Team
    0.70
    İĭ
    0.68
    Team
    0.68
    axy
    0.67
    ģĸ
    0.67
     something
    0.66
     Kinnikuman
    0.65
    circle
    0.64
    Activations Density 0.101%

    No Known Activations