© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 7136
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and fluctuations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to changes and fluctuations in various systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Veter
    -0.89
    gur
    -0.83
    atown
    -0.74
     Certification
    -0.71
     pulp
    -0.69
    udeb
    -0.68
    unts
    -0.68
     Votes
    -0.67
    alty
    -0.65
    kit
    -0.65
    POSITIVE LOGITS
     fluctuations
    0.98
    gradient
    0.97
     traject
    0.94
     unpredict
    0.94
     occurring
    0.92
     observable
    0.92
     phenomena
    0.88
     instability
    0.87
     patterns
    0.87
     arising
    0.87
    Activations Density 0.256%

    No Known Activations