Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16869
    Prev
    Next
    INDEX
    Explanations

    the phrase "all the time"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "all the time."

    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
    ync
    -0.73
    FUL
    -0.66
    PLA
    -0.63
    ful
    -0.62
    ndum
    -0.60
    arium
    -0.60
    Listener
    -0.59
    eming
    -0.58
    mma
    -0.58
    SPONSORED
    -0.58
    POSITIVE LOGITS
     way
    1.31
     time
    1.06
    ways
    0.93
     WAY
    0.91
    WAY
    0.89
     goddamn
    0.87
    way
    0.86
     same
    0.85
    time
    0.80
    together
    0.79
    Activations Density 0.031%

    No Known Activations