© 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. 13839
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "later on"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "later on" in various contexts

    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
     liter
    -0.70
     Ming
    -0.60
     Fram
    -0.59
    States
    -0.59
    leigh
    -0.57
     Compatibility
    -0.57
    facts
    -0.56
    Prim
    -0.54
    Cat
    -0.53
    ring
    -0.53
    POSITIVE LOGITS
    shore
    1.08
    erous
    1.07
     behalf
    1.00
    etime
    0.98
     occasion
    0.93
    site
    0.90
    side
    0.86
    etheless
    0.86
    yx
    0.81
    stage
    0.81
    Activations Density 0.072%

    No Known Activations