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. 21419
    Prev
    Next
    INDEX
    Explanations

    words related to significant anniversaries or jubilees

    oai_token-act-pair · gpt-3.5-turbo

    words related to anniversaries and significant celebrations

    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
     lawy
    -0.79
    TOP
    -0.64
    below
    -0.63
     trained
    -0.62
     NEC
    -0.61
     hospitals
    -0.61
     behav
    -0.58
     cured
    -0.58
     doctors
    -0.57
     pneumonia
    -0.56
    POSITIVE LOGITS
    ennial
    1.39
    enary
    1.10
     Anniversary
    0.99
    iversary
    0.94
     anniversary
    0.92
     celebrations
    0.89
     commem
    0.88
     Celebration
    0.86
    ilee
    0.85
    issance
    0.83
    Activations Density 0.011%

    No Known Activations