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. 13047
    Prev
    Next
    INDEX
    Explanations

    times mentioned in hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a specific time or approximate temporal references

    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
    rog
    -0.64
    eming
    -0.61
    atro
    -0.58
    yet
    -0.57
     Masquerade
    -0.56
    Sent
    -0.56
     indeed
    -0.55
    oran
    -0.54
    Auth
    -0.54
    oleon
    -0.54
    POSITIVE LOGITS
     midday
    1.03
     noon
    1.00
     1900
    0.97
     midnight
    0.94
     7000
    0.94
     3000
    0.94
     9000
    0.94
     1850
    0.94
     1400
    0.93
     1700
    0.91
    Activations Density 0.055%

    No Known Activations