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. 4-RES-JB
    6. 3805
    Prev
    Next
    INDEX
    Explanations

    mentions of the geographical location "Sumatra"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location, Sumatra

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

    No Comments

    Negative Logits
     livest
    -0.72
    Magikarp
    -0.64
    RAFT
    -0.63
    avorite
    -0.62
     subconscious
    -0.61
     surn
    -0.61
     blinking
    -0.61
    GMT
    -0.61
     listening
    -0.60
     tradem
    -0.60
    POSITIVE LOGITS
    ming
    1.20
    mers
    1.13
    mons
    1.05
    mits
    1.03
    atra
    1.00
    otaur
    1.00
    sum
    0.98
    itar
    0.96
    mar
    0.91
    ption
    0.91
    Activations Density 0.009%

    No Known Activations