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. 18446
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential impact or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a significant impact or consequence

    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
    atin
    -0.75
    bery
    -0.74
    iscover
    -0.72
     mash
    -0.69
    atism
    -0.66
    [/
    -0.62
    iasis
    -0.59
    fest
    -0.59
     Lust
    -0.59
    ighting
    -0.58
    POSITIVE LOGITS
     repercussions
    1.36
     ramifications
    1.33
     implications
    1.32
     consequences
    1.23
     unintended
    1.14
     profound
    1.13
     unforeseen
    1.09
     adverse
    1.05
     ripple
    1.03
     detrimental
    1.02
    Activations Density 0.145%

    No Known Activations