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. 6731
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the creation or customization of personal items or experiences

    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
    anwhile
    -0.85
    lehem
    -0.83
     Mub
    -0.83
    hovah
    -0.71
    akings
    -0.69
    ishops
    -0.67
    EGIN
    -0.66
    ynchronous
    -0.66
    hesda
    -0.66
    itement
    -0.65
    POSITIVE LOGITS
     version
    0.88
     custom
    0.84
     customized
    0.84
     personal
    0.80
     backyard
    0.77
     personalized
    0.75
     copy
    0.74
     accord
    0.74
     selves
    0.73
     homegrown
    0.71
    Activations Density 0.037%

    No Known Activations