© 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. 9-RES-JB
    11. 7520
    Prev
    Next
    INDEX
    Explanations

    phrases related to time frames and completion of tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time frames for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eman
    -0.61
    emy
    -0.58
    allic
    -0.56
    MD
    -0.56
    intel
    -0.56
    jing
    -0.55
    ensitive
    -0.55
    Collect
    -0.54
    affer
    -0.54
    itiz
    -0.54
    POSITIVE LOGITS
     seconds
    1.35
     minutes
    1.22
     Seconds
    1.20
     blink
    1.16
    seconds
    1.14
     hours
    1.12
     milliseconds
    1.11
     days
    1.08
     hour
    1.06
     weeks
    1.05
    Activations Density 0.510%

    No Known Activations