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. 8-RES-JB
    6. 16452
    Prev
    Next
    INDEX
    Explanations

    words related to splashing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "spl" within words

    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
     negligence
    -0.79
    culosis
    -0.66
    ³³³³³³³³³³³³³³³³
    -0.65
    IAS
    -0.65
     Moder
    -0.62
    manship
    -0.61
    PRES
    -0.61
    Reviewer
    -0.60
    agara
    -0.60
    GROUND
    -0.59
    POSITIVE LOGITS
    atoon
    1.18
    attered
    1.16
    atters
    1.12
    atter
    1.11
    ashing
    1.05
    inters
    1.05
    ashes
    0.97
    ashed
    0.94
    attering
    0.93
    iple
    0.92
    Activations Density 0.021%

    No Known Activations