© 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. 3-RES-JB
    11. 12338
    Prev
    Next
    INDEX
    Explanations

    phrases related to event organization and planners

    oai_token-act-pair · gpt-3.5-turbo

    references to event organizers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    croft
    -0.85
    bole
    -0.78
    eely
    -0.69
    olit
    -0.66
    PASS
    -0.64
    rises
    -0.64
    ault
    -0.64
    pathy
    -0.63
    ths
    -0.62
     Leopard
    -0.61
    POSITIVE LOGITS
     organizer
    0.88
     organizers
    0.84
     organisers
    0.79
    stration
    0.77
    ãĤ±
    0.77
    eers
    0.74
     Organ
    0.70
    paces
    0.70
     affiliate
    0.69
    ĸļ
    0.69
    Activations Density 0.018%

    No Known Activations