© 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. 2-RES-JB
    6. 11845
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "not only" is used before a statement emphasizing an additional point

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not only" which indicates additional points or clauses in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.81
    idon
    -0.66
    multipl
    -0.65
    )))
    -0.63
     Mushroom
    -0.62
    iths
    -0.60
     largeDownload
    -0.60
    ONG
    -0.58
    arted
    -0.58
    MU
    -0.57
    POSITIVE LOGITS
     marginally
    0.80
     omit
    0.71
     incidentally
    0.71
    phies
    0.70
     anymore
    0.69
     sparing
    0.67
     limited
    0.65
    ifiable
    0.65
     passively
    0.64
    ices
    0.63
    Activations Density 0.058%

    No Known Activations