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

    Neuronpedia

    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. 1-RES-JB
    11. 3911
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "gravitational lensing"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Rav" or its variants, indicating a focus on a specific person or topic related to "Rav."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lder
    -0.76
    ħĭ
    -0.66
    print
    -0.64
     cider
    -0.64
     Catalyst
    -0.63
     testify
    -0.62
     Forth
    -0.61
    drm
    -0.61
    ça
    -0.61
    vironment
    -0.59
    POSITIVE LOGITS
    rav
    1.09
    itational
    1.03
    iev
    0.89
    iral
    0.83
    aband
    0.83
    onite
    0.82
     Vaugh
    0.82
    atile
    0.79
    ulsion
    0.79
    oslav
    0.78
    Activations Density 0.006%

    No Known Activations