© 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. 10-RES-JB
    6. 6577
    Prev
    Next
    INDEX
    Explanations

    phrases pointing out or emphasizing something specific as exceptional or noteworthy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one" and its variations

    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
    inity
    -0.67
    incinn
    -0.67
    ility
    -0.66
     srf
    -0.66
    osponsors
    -0.64
    respective
    -0.62
    tnc
    -0.62
    edIn
    -0.62
    orically
    -0.59
    inders
    -0.59
    POSITIVE LOGITS
    hots
    1.04
     Hundred
    0.94
     hundred
    0.90
    alian
    0.89
     sided
    0.80
    =-=-=-=-
    0.79
    esan
    0.77
    idas
    0.75
    atic
    0.75
     eyed
    0.74
    Activations Density 0.052%

    No Known Activations