© 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. 8-RES-JB
    11. 20331
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and frequencies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to frequency and temporal occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tymology
    -0.73
    artisan
    -0.70
    ozy
    -0.68
    osate
    -0.67
    ibaba
    -0.66
    ersive
    -0.63
    uctor
    -0.62
    trak
    -0.61
     prevailed
    -0.60
    rote
    -0.60
    POSITIVE LOGITS
    minute
    0.79
     imaginable
    0.72
     thereafter
    0.71
     seconds
    0.69
     minutes
    0.68
     milliseconds
    0.67
    Saturday
    0.65
     minute
    0.65
     waking
    0.64
     ticks
    0.62
    Activations Density 0.054%

    No Known Activations