© 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. 8352
    Prev
    Next
    INDEX
    Explanations

    posts with the word "Post" with different numerical identifiers, likely indicating a specific type of content or categorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Post."

    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
     cane
    -0.66
     ages
    -0.62
     lovers
    -0.61
     cultiv
    -0.61
     escal
    -0.61
     heritage
    -0.61
     fir
    -0.60
     lover
    -0.60
     wolves
    -0.59
     barg
    -0.59
    POSITIVE LOGITS
    Post
    4.04
    post
    2.54
     Post
    2.41
    POST
    1.94
     post
    1.88
     POST
    1.60
    Posts
    1.45
     posts
    1.34
     Posts
    1.32
    posts
    1.30
    Activations Density 0.007%

    No Known Activations