Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20031
    Prev
    Next
    INDEX
    Explanations

    specific website names and associated information

    oai_token-act-pair · gpt-3.5-turbo

    domains related to online platforms or web properties

    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
     relax
    -0.66
     relaxation
    -0.66
     fragrance
    -0.65
     flask
    -0.64
     diam
    -0.64
     oun
    -0.64
     pipe
    -0.64
    ogh
    -0.64
    clus
    -0.63
     dos
    -0.63
    POSITIVE LOGITS
     Investigative
    0.93
     investigative
    0.87
    ishly
    0.78
     WATCHED
    0.78
    Daily
    0.78
    Magazine
    0.77
    Feed
    0.76
    blogs
    0.76
     Weekly
    0.76
    Fact
    0.75
    Activations Density 0.103%

    No Known Activations