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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19074
    Prev
    Next
    INDEX
    Explanations

    words related to variations, fluctuations, and changes in data or patterns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to climate variability and fluctuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilet
    -0.82
    Veter
    -0.74
     humble
    -0.73
    udeb
    -0.73
    ä¸Ĭ
    -0.70
    APTER
    -0.66
    unts
    -0.66
    atown
    -0.66
     clipboard
    -0.64
    UNCH
    -0.64
    POSITIVE LOGITS
     fluctuations
    0.98
    ilibrium
    0.94
    gradient
    0.88
     patterns
    0.87
     observable
    0.87
     observed
    0.85
     cycles
    0.83
     correlated
    0.83
     arising
    0.82
    rences
    0.82
    Activations Density 0.233%

    No Known Activations