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. 0-RES-JB
    6. 7057
    Prev
    Next
    INDEX
    Explanations

    words related to the physical planet earth

    oai_token-act-pair · gpt-3.5-turbo

    references to the planet Earth

    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
     Plugin
    -0.67
    abo
    -0.63
    _>
    -0.62
    Compl
    -0.60
    patient
    -0.59
    ano
    -0.59
    VPN
    -0.59
    Plugin
    -0.58
     Policies
    -0.58
     Lopez
    -0.57
    POSITIVE LOGITS
     earth
    3.87
     Earth
    2.71
    earth
    2.44
    Earth
    2.31
     planet
    1.58
     soil
    1.52
     earthly
    1.35
     terrestrial
    1.30
     globe
    1.21
     ground
    1.21
    Activations Density 0.010%

    No Known Activations