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. 21982
    Prev
    Next
    INDEX
    Explanations

    phrases related to repetitive actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to repetition and the concept of doing something multiple times

    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
    aria
    -0.67
     Minimum
    -0.64
    arine
    -0.57
    intent
    -0.57
     intimid
    -0.56
    ahime
    -0.55
    htaking
    -0.54
    minimum
    -0.54
    piring
    -0.54
    tackle
    -0.53
    POSITIVE LOGITS
     again
    2.20
     anew
    1.76
    again
    1.71
     Again
    1.49
     resumed
    1.36
     reapp
    1.34
     AGA
    1.28
    Again
    1.23
     rematch
    1.21
     reopen
    1.21
    Activations Density 1.122%

    No Known Activations