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. 9-RES-JB
    6. 21070
    Prev
    Next
    INDEX
    Explanations

    phrases containing the term "man-made"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to man-made environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grimes
    -0.66
     bitters
    -0.64
     Chambers
    -0.63
     0004
    -0.61
    =#
    -0.61
     waning
    -0.60
     Ces
    -0.59
     dim
    -0.58
     Blu
    -0.57
     Transcript
    -0.56
    POSITIVE LOGITS
    centered
    1.29
    centric
    1.18
    readable
    1.11
    rights
    1.07
    made
    1.07
    interest
    1.04
    shaped
    1.03
    eating
    1.01
    machine
    1.01
    killing
    1.00
    Activations Density 0.088%

    No Known Activations