© 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. 2-RES-JB
    11. 17529
    Prev
    Next
    INDEX
    Explanations

    phrases related to repetitions or practice

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reps" or variations of it, typically in the context of repetitive actions or practice

    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
    lihood
    -0.71
     Galile
    -0.70
     Spit
    -0.69
     Sark
    -0.65
    FACE
    -0.64
     Petroleum
    -0.64
     Sul
    -0.64
    ous
    -0.63
     Gas
    -0.63
    OUS
    -0.63
    POSITIVE LOGITS
     tremend
    1.38
    onse
    1.08
    undown
    0.91
    utations
    0.90
    ensional
    0.89
     reps
    0.88
    arious
    0.86
    olicy
    0.85
     describ
    0.85
    uters
    0.85
    Activations Density 0.010%

    No Known Activations