© 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. 19428
    Prev
    Next
    INDEX
    Explanations

    phrases referring to "the next generation" or "a new era" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to different generations and their characteristics or qualities

    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
    ptoms
    -0.73
    ousands
    -0.71
     Provided
    -0.70
     sqor
    -0.67
    rm
    -0.66
     ILCS
    -0.66
    vic
    -0.65
     beforehand
    -0.64
    whelming
    -0.63
    orst
    -0.63
    POSITIVE LOGITS
     warfare
    0.92
     computing
    0.90
     reckoning
    0.78
     exploration
    0.74
     storytelling
    0.72
     disruptive
    0.71
     combating
    0.67
     reversible
    0.66
     contro
    0.66
     colonization
    0.66
    Activations Density 0.217%

    No Known Activations