© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15552
    Prev
    Next
    INDEX
    Explanations

    content related to organized activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "organized"

    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
    £
    -0.92
     £
    -0.76
    frog
    -0.65
     Swan
    -0.65
     (£
    -0.64
     Ashes
    -0.64
    aren
    -0.63
     Tas
    -0.62
     apologise
    -0.61
    allow
    -0.61
    POSITIVE LOGITS
     organized
    3.85
     organised
    2.97
    organized
    2.58
     organize
    2.09
     organizing
    1.88
     arranged
    1.65
     organizer
    1.57
     coordinated
    1.54
     Organ
    1.50
     organizers
    1.45
    Activations Density 0.015%

    No Known Activations