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. 10-RES-JB
    6. 14823
    Prev
    Next
    INDEX
    Explanations

    instances where a sentence ends with a specific punctuation pattern

    oai_token-act-pair · gpt-3.5-turbo

    informal or casual references to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.82
     quir
    -0.82
    yip
    -0.80
     eleph
    -0.77
     prosec
    -0.74
     coral
    -0.71
     neb
    -0.71
     affili
    -0.69
     oath
    -0.68
     predis
    -0.68
    POSITIVE LOGITS
    Eventually
    2.07
    Then
    2.01
    Later
    1.94
    Soon
    1.93
    After
    1.84
    Shortly
    1.84
    Suddenly
    1.78
    Within
    1.76
    Upon
    1.75
    Initially
    1.68
    Activations Density 0.436%

    No Known Activations