© 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. 9-RES-JB
    11. 3185
    Prev
    Next
    INDEX
    Explanations

    references to past events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "past" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NEY
    -0.76
    MORE
    -0.65
    SOURCE
    -0.64
    wagon
    -0.63
    shapeshifter
    -0.63
    anguage
    -0.62
    strap
    -0.57
     exponentially
    -0.56
    SO
    -0.56
    lee
    -0.56
    POSITIVE LOGITS
    ebin
    1.73
    ures
    1.23
    iche
    1.09
    oral
    1.02
    ime
    1.01
     tense
    0.96
    orate
    0.95
    ured
    0.93
    ure
    0.93
    imes
    0.91
    Activations Density 0.033%

    No Known Activations