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. 19387
    Prev
    Next
    INDEX
    Explanations

    the concept of singularity or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a singular significant concept or instance

    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
    apons
    -0.74
    ammers
    -0.73
    enery
    -0.70
    osponsors
    -0.70
    ordes
    -0.69
    odore
    -0.69
    etti
    -0.66
    ories
    -0.65
     noses
    -0.64
    jong
    -0.62
    POSITIVE LOGITS
     thing
    1.19
     reason
    1.07
     hundred
    0.99
     aspect
    0.99
     of
    0.98
     manifestation
    0.97
     sided
    0.96
     example
    0.91
     indication
    0.90
     way
    0.88
    Activations Density 0.054%

    No Known Activations