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. 172
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consist" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the composition or make-up of something

    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
    ilings
    -0.67
    hound
    -0.65
    Hill
    -0.64
    eden
    -0.64
    hawks
    -0.64
     guiActiveUnfocused
    -0.62
    bell
    -0.61
    idge
    -0.61
    ils
    -0.59
    inn
    -0.58
    POSITIVE LOGITS
     chiefly
    0.87
     solely
    0.86
     mainly
    0.86
     consist
    0.83
     principally
    0.80
     primarily
    0.78
     comprised
    0.76
    ngth
    0.74
    ateurs
    0.71
    itute
    0.71
    Activations Density 0.032%

    No Known Activations