© 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. 7-RES-JB
    11. 2950
    Prev
    Next
    INDEX
    Explanations

    instances of patterns where the phrase "part of a" occurs

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of group or collective entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ians
    -0.82
    coins
    -0.79
    aires
    -0.76
    arians
    -0.75
     gays
    -0.75
     Ukrainians
    -0.74
    agents
    -0.74
     Russians
    -0.73
     Romans
    -0.73
    uses
    -0.72
    POSITIVE LOGITS
     larger
    1.07
     constellation
    1.00
     broader
    0.99
     continuum
    0.97
     sizeable
    0.92
     piece
    0.91
     plethora
    0.90
     wider
    0.89
     multitude
    0.89
     sizable
    0.85
    Activations Density 0.179%

    No Known Activations