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. 20032
    Prev
    Next
    INDEX
    Explanations

    phrases related to man-made things or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to human-induced environmental issues, particularly pollution and climate change

    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
     bitters
    -0.69
     Ces
    -0.68
     shutter
    -0.66
     Chambers
    -0.65
     Resort
    -0.64
     Hib
    -0.63
     deposit
    -0.62
     sunset
    -0.62
     Mehran
    -0.61
     Hick
    -0.61
    POSITIVE LOGITS
    centered
    1.38
    made
    1.34
    sized
    1.28
    machine
    1.27
    eating
    1.24
    shaped
    1.22
    centric
    1.22
    readable
    1.20
    dominated
    1.18
    specific
    1.16
    Activations Density 0.053%

    No Known Activations