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. 11-RES-JB
    6. 8240
    Prev
    Next
    INDEX
    Explanations

    phrases related to disparities or differences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of gaps, particularly social or economic disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGHTS
    -0.66
    ongyang
    -0.65
     Selected
    -0.62
    RAW
    -0.60
    der
    -0.60
     rpm
    -0.59
     vic
    -0.58
     Plant
    -0.58
    vale
    -0.58
    vez
    -0.57
    POSITIVE LOGITS
     between
    1.26
    between
    1.18
     separating
    1.04
     Between
    0.99
     widened
    0.97
     wid
    0.95
     widening
    0.93
     widen
    0.93
     gap
    0.92
     narrowing
    0.86
    Activations Density 0.091%

    No Known Activations