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. 6-RES-JB
    6. 22917
    Prev
    Next
    INDEX
    Explanations

    words related to cycles or recurring patterns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cycles or repetitive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inez
    -0.93
    essors
    -0.87
    imus
    -0.84
    amina
    -0.84
    avez
    -0.84
    orage
    -0.79
    roit
    -0.79
    awaru
    -0.78
    initions
    -0.78
    ractive
    -0.76
    POSITIVE LOGITS
     cycle
    1.14
     Cycle
    0.95
     cycles
    0.94
    cycle
    0.91
    cycles
    0.90
    cles
    0.84
     erg
    0.83
     repeats
    0.80
     alternating
    0.75
     Delay
    0.73
    Activations Density 0.022%

    No Known Activations