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. 7-RES-JB
    6. 24419
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison to something being perceived as less significant or valuable

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "nothing more than" to critique or diminish the significance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hare
    -0.82
    days
    -0.69
    xtap
    -0.65
    oak
    -0.63
    osen
    -0.63
     Souls
    -0.59
    æ©
    -0.58
    stown
    -0.57
    selves
    -0.57
    Lock
    -0.57
    POSITIVE LOGITS
     than
    0.96
     akin
    0.87
     importantly
    0.79
     inclined
    0.77
     resembling
    0.74
     manageable
    0.74
     ado
    0.73
     mathemat
    0.71
     nor
    0.69
     happ
    0.69
    Activations Density 0.025%

    No Known Activations