© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11502
    Prev
    Next
    INDEX
    Explanations

    adverbs modified by "naturally"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of natural occurrences or naturalness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.67
     Millennium
    -0.67
    andals
    -0.66
     Straw
    -0.66
    rity
    -0.64
    anmar
    -0.64
    ammy
    -0.63
    berman
    -0.63
    rav
    -0.62
    ewski
    -0.61
    POSITIVE LOGITS
     occurring
    1.03
     inclined
    0.83
    istic
    0.81
    uces
    0.80
     arises
    0.80
    occ
    0.77
    istically
    0.76
     combust
    0.73
    uced
    0.73
    isable
    0.72
    Activations Density 0.026%

    No Known Activations