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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19355
    Prev
    Next
    INDEX
    Explanations

    fluctuations and trends in data over time

    oai_token-act-pair · gpt-3.5-turbo

    references to fluctuations or changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voic
    -0.79
     oath
    -0.79
     pulp
    -0.69
     insulted
    -0.64
     offended
    -0.62
    VICE
    -0.61
     makeshift
    -0.61
     authent
    -0.60
     lawy
    -0.59
     entert
    -0.59
    POSITIVE LOGITS
    flation
    0.97
     peaks
    0.93
     recession
    0.90
     Recession
    0.88
     exponential
    0.87
     gradual
    0.84
     plateau
    0.84
    Chart
    0.82
    Figure
    0.81
    iatus
    0.81
    Activations Density 1.345%

    No Known Activations