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. 19349
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing and discussing personal opinions and views

    oai_token-act-pair · gpt-3.5-turbo

    references to personal opinions or perspectives

    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
     Dull
    -0.75
    trap
    -0.67
    insert
    -0.64
     unbeliev
    -0.64
    Textures
    -0.63
    cia
    -0.63
    dry
    -0.63
    eri
    -0.62
    duct
    -0.62
    Sequ
    -0.61
    POSITIVE LOGITS
     stances
    1.18
     beliefs
    1.05
     stance
    0.97
     expressed
    0.96
     opinions
    0.95
     regarding
    0.91
     views
    0.91
    odox
    0.91
     viewpoints
    0.91
     esp
    0.86
    Activations Density 0.144%

    No Known Activations