Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8833
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases related to decorations and aesthetics, particularly for events

    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
     millenn
    -0.62
    itivity
    -0.60
     controversies
    -0.53
     recent
    -0.53
     sophistication
    -0.53
     globalization
    -0.53
     Dynamics
    -0.52
     latent
    -0.52
    esta
    -0.52
     persistence
    -0.51
    POSITIVE LOGITS
     lest
    1.20
     instead
    1.17
     ASAP
    1.07
     unless
    1.07
    instead
    1.01
     indefinitely
    0.99
     tomorrow
    0.95
     whenever
    0.89
     someday
    0.89
     if
    0.88
    Activations Density 0.841%

    No Known Activations