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. 6-RES-JB
    6. 15976
    Prev
    Next
    INDEX
    Explanations

    terms related to conservative or consensus viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cons" and its variations, indicating a focus on consumer-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WOOD
    -0.78
     horses
    -0.69
     Meadow
    -0.67
     Hoover
    -0.65
    ILLE
    -0.63
     Pegasus
    -0.62
     feed
    -0.62
    dogs
    -0.62
     Carnegie
    -0.61
     Lup
    -0.61
    POSITIVE LOGITS
    ervatives
    1.37
    piracy
    1.35
    ensual
    1.34
    umers
    1.28
    cientious
    1.28
    ensus
    1.24
    idered
    1.21
    istent
    1.18
    ervative
    1.17
    umption
    1.10
    Activations Density 0.009%

    No Known Activations