© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13925
    Prev
    Next
    INDEX
    Explanations

    references to blog-related content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Blog"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overpowered
    -0.69
    matched
    -0.67
     potassium
    -0.63
     overd
    -0.61
     matching
    -0.61
    esson
    -0.60
     dil
    -0.60
     arsenic
    -0.59
     illumination
    -0.59
     separately
    -0.59
    POSITIVE LOGITS
     Blog
    3.75
    Blog
    2.53
    blog
    2.14
     blog
    2.00
     blogs
    1.96
     blogging
    1.91
    blogs
    1.73
     blogger
    1.64
     Podcast
    1.61
     bloggers
    1.61
    Activations Density 0.008%

    No Known Activations