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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 12455
    Prev
    Next
    INDEX
    Explanations

    phrases related to slogans or mottos

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to slogans and mottos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idan
    -0.72
    eki
    -0.70
    edited
    -0.69
    NetMessage
    -0.66
    essions
    -0.66
    actions
    -0.66
    olia
    -0.65
    edu
    -0.64
    Medium
    -0.63
     contrace
    -0.63
    POSITIVE LOGITS
     slogan
    1.19
     slogans
    1.02
     motto
    0.87
     goodbye
    0.83
     proclaiming
    0.82
    terday
    0.79
     chanted
    0.76
     phrase
    0.71
    naire
    0.69
     "#
    0.68
    Activations Density 0.029%

    No Known Activations