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. 10842
    Prev
    Next
    INDEX
    Explanations

    phrases involving the process of obtaining something or progressing to a certain point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verbs "get" and "got."

    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
    uns
    -0.67
    orable
    -0.65
    stre
    -0.61
     Tanz
    -0.61
    onite
    -0.56
    umar
    -0.56
    oret
    -0.55
    deen
    -0.54
    bie
    -0.54
    often
    -0.53
    POSITIVE LOGITS
     rid
    0.92
     married
    0.90
     tired
    0.89
     bored
    0.88
     started
    0.88
     acquainted
    0.83
     settled
    0.81
     underway
    0.80
     booted
    0.78
     accustomed
    0.77
    Activations Density 0.088%

    No Known Activations