© 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. 1-RES-JB
    11. 23539
    Prev
    Next
    INDEX
    Explanations

    phrases related to time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "PT"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.82
    wind
    -0.65
    é¾įåĸļ士
    -0.64
     Hurricanes
    -0.64
     Heavenly
    -0.61
     resemblance
    -0.59
    keepers
    -0.57
     Ca
    -0.56
     lively
    -0.55
     Carib
    -0.54
    POSITIVE LOGITS
    ypes
    1.10
    EMBER
    1.08
    PT
    1.07
    ember
    0.92
    ournament
    0.84
    icket
    0.81
    itude
    0.81
    uple
    0.80
    ractor
    0.79
    ogether
    0.78
    Activations Density 0.004%

    No Known Activations