© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17260
    Prev
    Next
    INDEX
    Explanations

    specific times written in a particular format (e.g., "4.45 pm", "5.15 pm")

    oai_token-act-pair · gpt-3.5-turbo

    specific timestamps and locations related to events

    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
     Metatron
    -0.80
     Preferred
    -0.70
     Vault
    -0.69
    Favorite
    -0.65
     toget
    -0.62
     Pulitzer
    -0.62
    channelAvailability
    -0.61
     uptick
    -0.60
    CLASSIFIED
    -0.59
    reply
    -0.58
    POSITIVE LOGITS
    pm
    1.37
     BST
    1.22
    am
    1.18
     GMT
    1.09
    noon
    1.04
    GMT
    1.02
     pm
    0.98
    km
    0.95
     midday
    0.94
    icester
    0.90
    Activations Density 0.054%

    No Known Activations