© 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. 7-RES-JB
    11. 215
    Prev
    Next
    INDEX
    Explanations

    time-related phrases such as "within hours of," "days of," or "minutes after."

    oai_token-act-pair · gpt-3.5-turbo

    timelines and time-related phrases in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ń
    -0.80
     Cosponsors
    -0.78
    scar
    -0.74
    Pri
    -0.73
    Paul
    -0.69
    league
    -0.69
    pdf
    -0.68
    AFP
    -0.67
    Els
    -0.67
    Palest
    -0.66
    POSITIVE LOGITS
     checkout
    1.09
     expiration
    0.96
     onset
    0.87
     completion
    0.87
     meals
    0.87
     maturity
    0.83
     arrival
    0.82
     meal
    0.82
     embark
    0.82
     initiating
    0.82
    Activations Density 0.381%

    No Known Activations