© 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. 8-RES-JB
    11. 7894
    Prev
    Next
    INDEX
    Explanations

    specific incidents or events in news articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "that" used to introduce relative clauses or further information about events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hat
    -0.65
     guessing
    -0.65
    holding
    -0.62
     speaking
    -0.61
    river
    -0.61
     prescribing
    -0.60
    istance
    -0.60
     boarding
    -0.60
     Saying
    -0.59
     Eye
    -0.59
    POSITIVE LOGITS
     culminated
    1.38
     lasted
    1.35
     resulted
    1.30
     occurred
    1.23
     ensued
    1.17
     culmin
    1.17
     preceded
    1.17
     coincided
    1.13
     consisted
    1.03
     lasts
    1.02
    Activations Density 0.216%

    No Known Activations