© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10557
    Prev
    Next
    INDEX
    Explanations

    specific time periods or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time durations or periods of employment

    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
    pour
    -0.74
    certain
    -0.72
    hazard
    -0.67
    Maker
    -0.67
    cript
    -0.67
    aque
    -0.67
    sufficient
    -0.66
    VP
    -0.66
    eny
    -0.66
    sure
    -0.65
    POSITIVE LOGITS
    inka
    0.67
    terday
    0.67
    ithub
    0.66
    itures
    0.65
    ishers
    0.65
     proven
    0.64
    alde
    0.63
    unda
    0.63
     Til
    0.63
    soever
    0.63
    Activations Density 0.028%

    No Known Activations