© 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. 10-RES-JB
    11. 11423
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a period of time has passed

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.71
     unfocusedRange
    -0.71
    ply
    -0.63
     sqor
    -0.62
    future
    -0.61
    orah
    -0.60
     implication
    -0.59
    detail
    -0.59
     tomorrow
    -0.59
    PER
    -0.58
    POSITIVE LOGITS
     inception
    1.41
     debuted
    1.40
     began
    1.38
     started
    1.33
     launched
    1.21
     commenced
    1.19
     arrived
    1.16
     founded
    1.13
     transitioned
    1.12
     premiered
    1.10
    Activations Density 0.279%

    No Known Activations