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. 0-RES-JB
    6. 4659
    Prev
    Next
    INDEX
    Explanations

    references to the term "eagle" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to types of eagles and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĸº
    -0.71
     volume
    -0.68
     Que
    -0.66
     Yun
    -0.64
     Rapp
    -0.62
     Volume
    -0.62
     Hits
    -0.62
     volumes
    -0.62
     Souls
    -0.61
     Lime
    -0.61
    POSITIVE LOGITS
    agle
    3.59
    agles
    3.58
    gypt
    1.64
    clipse
    1.56
    verett
    1.48
    LEASE
    1.39
    agall
    1.19
    irie
    1.18
    ucl
    1.15
    mpire
    1.15
    Activations Density 0.036%

    No Known Activations