Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15144
    Prev
    Next
    INDEX
    Explanations

    mention of the name "Dion."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people, particularly those named Dion and Dillon

    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
    berman
    -0.99
    glers
    -0.94
    ket
    -0.79
    âĸĪâĸĪ
    -0.74
    aten
    -0.74
    bing
    -0.73
    ken
    -0.72
    Score
    -0.72
    keleton
    -0.71
    erver
    -0.71
    POSITIVE LOGITS
     exch
    0.66
     Malfoy
    0.64
    agher
    0.64
     srf
    0.62
    interstitial
    0.62
     urgency
    0.61
    romeda
    0.60
    ysis
    0.60
     potency
    0.59
     futile
    0.59
    Activations Density 0.031%

    No Known Activations