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. 8-RES-JB
    6. 237
    Prev
    Next
    INDEX
    Explanations

    phrases related to viewpoints or ways of looking at things

    oai_token-act-pair · gpt-3.5-turbo

    references to different viewpoints or angles on a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.79
    liam
    -0.78
    ertodd
    -0.71
    avis
    -0.70
    nard
    -0.70
    ãĥīãĥ©
    -0.68
    zeb
    -0.68
    corn
    -0.66
    lez
    -0.66
    cakes
    -0.66
    POSITIVE LOGITS
     perspectives
    1.03
     perspective
    1.03
     viewpoint
    0.91
     Perspective
    0.89
     viewpoints
    0.84
     lens
    0.81
    spection
    0.79
     view
    0.79
     views
    0.78
     Lens
    0.75
    Activations Density 0.023%

    No Known Activations