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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 7272
    Prev
    Next
    INDEX
    Explanations

    phrases related to temporal sequencing or progression

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "once again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ype
    -0.73
    acht
    -0.71
    chens
    -0.69
    eme
    -0.68
    usha
    -0.65
    atches
    -0.64
    orts
    -0.64
    gement
    -0.63
    inters
    -0.63
    PsyNetMessage
    -0.62
    POSITIVE LOGITS
     again
    1.56
    again
    1.12
     Again
    1.10
    handedly
    1.03
     belonged
    0.87
    Again
    0.87
     AGA
    0.82
     famously
    0.80
     Upon
    0.79
     hailed
    0.76
    Activations Density 0.036%

    No Known Activations