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. 18128
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences in instructional or procedural text

    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
     indebted
    -0.84
     affili
    -0.79
     bonded
    -0.77
     contradicted
    -0.75
     evidenced
    -0.74
     waged
    -0.72
     contested
    -0.71
     prohib
    -0.71
     classified
    -0.71
     contests
    -0.69
    POSITIVE LOGITS
     Then
    1.71
     Afterwards
    1.54
     Alternatively
    1.53
     Repeat
    1.46
     Otherwise
    1.41
     Once
    1.37
     Depending
    1.35
     Ideally
    1.35
     Remove
    1.33
     Immediately
    1.31
    Activations Density 0.138%

    No Known Activations