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. 8-RES-JB
    6. 20958
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in "-ique" or "-iqu"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that contain the suffix "ique"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.76
     limp
    -0.72
    backer
    -0.64
     Bridgewater
    -0.62
    pora
    -0.61
     regress
    -0.61
    growth
    -0.60
     limbs
    -0.59
     positional
    -0.58
     Typhoon
    -0.58
    POSITIVE LOGITS
    entials
    0.86
    itous
    0.86
    ebook
    0.84
    unction
    0.84
    ueless
    0.84
    ues
    0.83
    eous
    0.83
    ifier
    0.78
    istries
    0.77
    ed
    0.77
    Activations Density 0.034%

    No Known Activations