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. 9-RES-JB
    6. 12973
    Prev
    Next
    INDEX
    Explanations

    instances of attention to detail and careful planning in design processes

    oai_token-act-pair · gpt-3.5-turbo

    references to thoughtful design and attention to detail in creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.83
     anymore
    -0.74
     ceases
    -0.71
     anytime
    -0.69
     resumed
    -0.69
     someday
    -0.68
     denies
    -0.66
     Appears
    -0.64
     haunt
    -0.64
    Charges
    -0.63
    POSITIVE LOGITS
     designing
    0.92
     design
    0.85
     meticulously
    0.82
     optimizing
    0.81
     simplicity
    0.81
     painstaking
    0.80
     prototypes
    0.78
     chosen
    0.75
     designers
    0.74
     templates
    0.73
    Activations Density 0.754%

    No Known Activations