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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-RES-JB
    6. 10680
    Prev
    Next
    INDEX
    Explanations

    terms related to systems or processes in different contexts, such as social dynamics, market dynamics, and engineering dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dynamics" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ht
    -0.76
     Hallow
    -0.73
    haar
    -0.65
     amend
    -0.63
    abetic
    -0.63
    aste
    -0.63
    printed
    -0.62
     Hok
    -0.62
    opened
    -0.62
    wards
    -0.62
    POSITIVE LOGITS
     dynamics
    3.51
     Dynamics
    2.04
     traject
    1.23
     rhythms
    1.16
    odynamics
    1.09
     atmosp
    1.06
     nuances
    1.04
     fundamentals
    1.00
     simulations
    1.00
     workings
    1.00
    Activations Density 0.019%

    No Known Activations