© 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. 6-RES-JB
    11. 23751
    Prev
    Next
    INDEX
    Explanations

    patterns related to changes and trends, especially those involving increases or declines

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words that indicate relationships or changes between different elements

    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
    è£ħ
    -0.68
    aves
    -0.67
    pton
    -0.66
    rera
    -0.65
    agram
    -0.64
     Bible
    -0.62
    VICE
    -0.62
    Ha
    -0.61
    onyms
    -0.60
    »Ĵ
    -0.60
    POSITIVE LOGITS
    flation
    0.79
     overshadow
    0.75
     stagn
    0.74
     Yen
    0.72
    gradient
    0.72
     polarization
    0.71
     deterioration
    0.71
     Slowly
    0.71
    luster
    0.70
    shr
    0.70
    Activations Density 0.532%

    No Known Activations