© 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. 10-RES-JB
    11. 20405
    Prev
    Next
    INDEX
    Explanations

    years and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to time and temporal entities, particularly years and durations

    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
    Magikarp
    -0.61
    ortun
    -0.60
    MAS
    -0.50
    ratulations
    -0.49
     glim
    -0.49
    atcher
    -0.48
    ERG
    -0.48
     Soph
    -0.48
    Sym
    -0.46
     NEVER
    -0.46
    POSITIVE LOGITS
    .�
    1.00
    .''.
    0.98
    .''
    0.92
    .*
    0.91
    _.
    0.85
    .[
    0.84
    .ãĢį
    0.84
    .
    0.84
    .</
    0.83
    .).
    0.83
    Activations Density 0.903%

    No Known Activations