© 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. 4-RES-JB
    11. 14791
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, specifically focusing on the current moment

    oai_token-act-pair · gpt-3.5-turbo

    references to the present time or current situations

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

    No Comments

    Negative Logits
    emale
    -0.71
    remlin
    -0.69
    friends
    -0.65
    onto
    -0.63
    aped
    -0.63
    PAR
    -0.62
    CHQ
    -0.62
    MET
    -0.62
    gregation
    -0.61
    guy
    -0.61
    POSITIVE LOGITS
    aries
    0.88
    aneously
    0.84
     moment
    0.80
    abouts
    0.79
    ary
    0.77
    endment
    0.70
     totality
    0.70
    xus
    0.69
    ogen
    0.69
    hift
    0.68
    Activations Density 0.015%

    No Known Activations