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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3508
    Prev
    Next
    INDEX
    Explanations

    timestamps or dates related to the word "Last" in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to recency or timeliness of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbuds
    -0.68
    onto
    -0.67
    cil
    -0.63
    obin
    -0.63
    OPLE
    -0.63
    urious
    -0.62
    sure
    -0.60
    aii
    -0.59
    plain
    -0.58
    odium
    -0.58
    POSITIVE LOGITS
     updated
    1.09
     rites
    1.05
     edited
    1.04
     bumped
    1.03
     Updated
    1.02
     modified
    0.96
     seen
    0.95
     night
    0.91
     Seen
    0.91
     Modified
    0.90
    Activations Density 0.055%

    No Known Activations