© 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. 1-RES-JB
    11. 20371
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of fluctuation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes or variability in data, particularly focusing on fluctuations and oscillations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.92
    20439
    -0.80
    HCR
    -0.75
    Honest
    -0.70
    ESCO
    -0.70
    éĹĺ
    -0.68
    Exc
    -0.67
    cott
    -0.66
    earable
    -0.66
    ä½ľ
    -0.66
    POSITIVE LOGITS
    uating
    1.34
     fluct
    1.32
     oscill
    1.25
    uates
    1.19
    uation
    1.18
     fluctuations
    1.16
    uate
    1.13
    uated
    1.00
    scill
    0.93
     capacitor
    0.93
    Activations Density 0.014%

    No Known Activations