© 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. 10-RES-JB
    11. 7758
    Prev
    Next
    INDEX
    Explanations

    phrases related to transforming or converting things

    oai_token-act-pair · gpt-3.5-turbo

    instances of transformation or conversion of one thing into another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cies
    -0.75
    rez
    -0.73
    ellen
    -0.69
    ritz
    -0.68
    erest
    -0.68
    ername
    -0.68
    cation
    -0.67
    there
    -0.67
    affected
    -0.67
    most
    -0.66
    POSITIVE LOGITS
     something
    1.07
     usable
    0.88
     a
    0.84
     an
    0.81
     adulthood
    0.76
     mush
    0.71
     manageable
    0.68
     mindless
    0.67
     fodder
    0.66
     reality
    0.66
    Activations Density 0.103%

    No Known Activations