Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1690
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of the past

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "past."

    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
    shapeshifter
    -0.77
    anguage
    -0.69
    wagon
    -0.65
    zhen
    -0.62
    NEY
    -0.62
    starting
    -0.60
    mand
    -0.60
    Downloadha
    -0.59
     Gong
    -0.58
    Te
    -0.58
    POSITIVE LOGITS
    ebin
    1.59
    ures
    1.15
    ime
    1.15
    iche
    1.13
     tense
    1.10
    imes
    1.06
    orate
    0.99
    oral
    0.96
    ure
    0.88
    ured
    0.86
    Activations Density 0.031%

    No Known Activations